© 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. 99470
    Prev
    Next
    INDEX
    Explanations

    I think

    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
    鸶
    -2.08
    7
    -2.02
     in
    -1.93
    This
    -1.91
     They
    -1.91
     Both
    -1.86
     With
    -1.85
    nasional
    -1.83
     While
    -1.83
     =
    -1.83
    POSITIVE LOGITS
     två
    1.61
     också
    1.51
    おまけ
    1.45
    最初は
    1.45
    他に
    1.43
     fyra
    1.43
    どっち
    1.43
    ↵↵
    1.42
     dwóch
    1.39
    w
    1.39
    Activations Density 0.046%

    No Known Activations