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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58311
    Prev
    Next
    INDEX
    Explanations

    events involving death or disaster

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     so
    -0.88
    Delayed
    -0.78
     دچار
    -0.77
    넬
    -0.76
     in
    -0.75
    скільки
    -0.74
     logam
    -0.73
     does
    -0.71
     场
    -0.71
    ၄
    -0.71
    POSITIVE LOGITS
    龊
    0.89
    ENBERG
    0.84
    LITERATURE
    0.83
    TÜ
    0.83
    iast
    0.82
    LoginPage
    0.82
    predictor
    0.82
    És
    0.82
     spender
    0.81
     alanı
    0.81
    Activations Density 0.139%

    No Known Activations