© 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. 117545
    Prev
    Next
    INDEX
    Explanations

    static final or readonly

    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
    طرف
    -0.84
    覧
    -0.83
    監修
    -0.83
     its
    -0.82
    τερ
    -0.82
     everything
    -0.81
     publico
    -0.81
    创始人
    -0.81
    relser
    -0.80
    Ᏸ
    -0.78
    POSITIVE LOGITS
    }}_{\
    0.91
     Вікі
    0.90
    などの
    0.85
     долла
    0.84
    iar
    0.83
     final
    0.83
    cyjne
    0.82
     tropicales
    0.82
    Después
    0.82
    HOLD
    0.81
    Activations Density 0.003%

    No Known Activations