© 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. 58511
    Prev
    Next
    INDEX
    Explanations

    multiplication and multiplicative groups

    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
     dissenting
    -0.78
     fortitude
    -0.78
     adaptations
    -0.78
    {
    -0.77
     continues
    -0.77
    恿
    -0.77
    aternal
    -0.77
    🤢
    -0.76
    有力
    -0.75
    чева
    -0.75
    POSITIVE LOGITS
    plication
    0.97
     by
    0.97
    multip
    0.96
     factors
    0.95
     multip
    0.94
     ers
    0.93
     Madness
    0.92
    arity
    0.91
     tablespoon
    0.88
    Ху
    0.87
    Activations Density 0.010%

    No Known Activations