© 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. 10-GEMMASCOPE-RES-131K
    7. 14232
    Prev
    Next
    INDEX
    Explanations

    storms and their effects

    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_10/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
     był
    -2.05
    ’
    -1.78
    zembro
    -1.77
     était
    -1.75
    稗
    -1.73
    ">
    -1.68
    </em>
    -1.60
    </h2>
    -1.55
    lebo
    -1.54
    膦
    -1.52
    POSITIVE LOGITS
    ↵↵
    1.83
    谄
    1.75
     dijeron
    1.58
    ቷ
    1.58
     wichtig
    1.55
     are
    1.46
     perfetta
    1.46
    珍しい
    1.45
     ridurre
    1.45
     meravigli
    1.45
    Activations Density 0.020%

    No Known Activations