© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8175
    Prev
    Next
    INDEX
    Explanations

    SpriteKit game development concepts

    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
    there
    -1.88
    o
    -1.72
    in
    -1.71
    ’
    -1.52
     but
    -1.45
     since
    -1.43
    begin
    -1.42
    of
    -1.38
     There
    -1.38
    on
    -1.38
    POSITIVE LOGITS
     dezelve
    1.63
    </b>
    1.56
    Conclusión
    1.52
     clás
    1.45
    ㈮
    1.42
     weihnachts
    1.39
    ==""){
    1.39
    凇
    1.38
     ')[
    1.35
     frescas
    1.34
    Activations Density 0.009%

    No Known Activations