© 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. 78529
    Prev
    Next
    INDEX
    Explanations

    game mechanics and values

    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
     aven
    -0.79
    statistical
    -0.76
     STATS
    -0.75
     metri
    -0.74
     magaz
    -0.73
     Stats
    -0.71
     Seer
    -0.71
     veu
    -0.71
     Statistical
    -0.71
    riez
    -0.71
    POSITIVE LOGITS
     investigation
    0.85
     Knowledge
    0.85
     history
    0.84
     Craft
    0.83
     апте
    0.80
     Investigation
    0.79
     History
    0.79
     ranks
    0.78
     Recognize
    0.78
     craft
    0.77
    Activations Density 0.012%

    No Known Activations