© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50254
    Prev
    Next
    INDEX
    Explanations

    conditional or occasional occurrences

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of numerical probabilities, odds, or frequency expressions (e.g. “3 in 5 times,” “randomly,” “odds,” percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    descriptions of technical problems or issues occurring intermittently or under specific conditions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of problems that occur intermittently or under specific conditions, using qualifiers about frequency, timing, randomness, or limited scope.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.40
    不小心
    -1.19
     благодаря
    -1.15
    文化
    -1.14
     sayesinde
    -1.13
     согласно
    -1.11
     vì
    -1.10
     kerana
    -1.06
     RBIs
    -1.02
     thanks
    -1.00
    POSITIVE LOGITS
     consistently
    1.32
     seemingly
    1.15
    symptoms
    1.13
    Symptoms
    1.13
    这个问题
    1.09
     Besøkt
    1.08
    ன்று
    1.05
    店長
    1.05
     seemed
    1.05
     symptom
    1.04
    Activations Density 0.179%

    No Known Activations