© 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. 10-GEMMASCOPE-RES-131K
    7. 19031
    Prev
    Next
    INDEX
    Explanations

    unwanted items or outcomes

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

    The neuron consistently fires on occurrences of the adjective “unwanted.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    拚
    -2.50
     {
    -2.44
    乄
    -2.42
    despite
    -2.34
    瘣
    -2.31
    ⧠
    -2.17
    骉
    -2.11
    慫
    -2.08
    ing
    -2.05
     Kraków
    -2.03
    POSITIVE LOGITS
     These
    2.64
     andere
    2.41
    er
    2.39
    These
    2.31
    is
    2.23
     exquisite
    2.16
     kaas
    2.08
    最重要
    2.05
    突破
    2.02
    واصل
    1.98
    Activations Density 0.001%

    No Known Activations