© 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. 22-GEMMASCOPE-RES-131K
    7. 65734
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by punctuation/letters

    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_22/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
    スン
    -0.90
     expl
    -0.87
     explication
    -0.86
    weth
    -0.85
     immunos
    -0.85
     alcune
    -0.85
    ஐ
    -0.85
     exe
    -0.84
    Jaguar
    -0.84
     extraña
    -0.84
    POSITIVE LOGITS
    ｿ
    0.91
     other
    0.88
     (
    0.88
     additional
    0.88
     or
    0.87
     as
    0.86
     in
    0.86
     which
    0.85
    just
    0.84
     menyal
    0.83
    Activations Density 0.080%

    No Known Activations