© 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. 78468
    Prev
    Next
    INDEX
    Explanations

    top chart positions

    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
     gustaba
    -0.82
    単語
    -0.77
    destruct
    -0.75
    truct
    -0.74
    が一番
    -0.74
    FOTOS
    -0.74
    さり
    -0.73
    ボス
    -0.73
     quedo
    -0.73
    bende
    -0.73
    POSITIVE LOGITS
     Top
    2.80
     top
    2.61
    Top
    2.30
     TOP
    1.88
    top
    1.72
    TOP
    1.63
     топ
    1.55
     within
    1.50
     among
    1.40
    トップ
    1.28
    Activations Density 0.043%

    No Known Activations