© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4267
    Prev
    Next
    INDEX
    Explanations

    Boost Software License

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

    This neuron activates on numeric literals (multi-digit numbers).

    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
    CAROL
    -0.69
     remake
    -0.69
     IAM
    -0.67
     Cava
    -0.67
     descente
    -0.65
     Diner
    -0.65
     cover
    -0.65
     unité
    -0.64
    ペア
    -0.63
    ická
    -0.63
    POSITIVE LOGITS
     друзьями
    0.88
     padrão
    0.82
    ссов
    0.75
    甭
    0.73
    тельстве
    0.72
     nullptr
    0.72
    班级
    0.72
     bénéfic
    0.71
    alem
    0.70
    uot
    0.69
    Activations Density 0.034%

    No Known Activations