© 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. 25948
    Prev
    Next
    INDEX
    Explanations

    Code, language, and domain-specific identifiers

    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
     Вале
    -0.95
     Tanpa
    -0.92
     државе
    -0.90
     versione
    -0.89
    Nå
    -0.87
    Dziękuję
    -0.86
     {?
    -0.86
     عملية
    -0.84
    CurrentValue
    -0.84
     said
    -0.83
    POSITIVE LOGITS
     bijzondere
    1.02
     inscri
    0.92
    イカ
    0.91
    可以说
    0.85
     Protects
    0.84
     Dorado
    0.83
     stren
    0.83
    Psico
    0.83
    wsze
    0.82
     enro
    0.82
    Activations Density 0.002%

    No Known Activations