© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    forced violence or confessions

    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
    ㎞
    -0.88
    ndorf
    -0.85
     díky
    -0.85
     plaît
    -0.82
    よろしくお願いします
    -0.81
     murdered
    -0.79
    assen
    -0.79
     tragedy
    -0.78
    슷
    -0.77
    RTLE
    -0.77
    POSITIVE LOGITS
     forced
    1.25
     repeatedly
    1.13
     forcing
    1.00
    continence
    0.95
    burning
    0.92
     force
    0.91
    wiring
    0.90
    forced
    0.90
    ют
    0.90
    Freezing
    0.89
    Activations Density 0.035%

    No Known Activations