© 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. 81164
    Prev
    Next
    INDEX
    Explanations

    kill/death/MVP

    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
     מיי
    -0.81
     Freitag
    -0.73
    rý
    -0.71
     Portuguese
    -0.69
    schedule
    -0.69
    窃
    -0.68
    UIButton
    -0.68
    üle
    -0.67
    Caller
    -0.66
     madam
    -0.66
    POSITIVE LOGITS
     kills
    1.78
     kill
    1.73
     killing
    1.44
    Kill
    1.34
     deaths
    1.34
    kills
    1.32
     killed
    1.30
     Kills
    1.30
     KILL
    1.29
    kill
    1.27
    Activations Density 0.007%

    No Known Activations