© 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. 65962
    Prev
    Next
    INDEX
    Explanations

    numbers following apostrophes or specific words

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

    This neuron detects numeric expressions and quantity indicators (e.g. standalone numbers, numeric tokens, and numeric prefixes) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Phosphorus
    -0.75
     localStorage
    -0.72
    babkan
    -0.71
     Như
    -0.69
     glau
    -0.69
    Rude
    -0.68
     də
    -0.68
    figs
    -0.68
    Spoilers
    -0.67
    NXG
    -0.67
    POSITIVE LOGITS
     上午
    0.93
    esModule
    0.76
     jButton
    0.76
    uvo
    0.75
    astă
    0.75
     بتاريخ
    0.75
    丰
    0.74
    ERN
    0.74
    ày
    0.73
     住宅
    0.72
    Activations Density 0.011%

    No Known Activations