© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129941
    Prev
    Next
    INDEX
    Explanations

    killing and death

    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_22/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
     concours
    -0.95
     ſi
    -0.93
    siger
    -0.93
    Ң
    -0.92
    ämään
    -0.92
    レディース
    -0.91
    esserts
    -0.91
     sterk
    -0.91
    侦
    -0.89
     exporter
    -0.88
    POSITIVE LOGITS
     by
    1.30
     chết
    1.07
     death
    1.05
     soziale
    1.05
     off
    1.03
     muere
    1.01
     deaths
    0.98
     sozialen
    0.98
     killed
    0.97
    的高
    0.96
    Activations Density 0.088%

    No Known Activations