© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
     kabát
    -1.02
    Zubereitung
    -0.99
    licante
    -0.98
     CONSE
    -0.96
    excellence
    -0.94
    Specifik
    -0.94
    FUENTES
    -0.94
     було
    -0.93
    饷
    -0.93
    APPENDICES
    -0.92
    POSITIVE LOGITS
    ❜
    0.93
     herausgegeben
    0.93
     与
    0.92
     given
    0.92
     unterstützt
    0.88
    the
    0.86
    VERSION
    0.86
    ⅕
    0.86
    Version
    0.85
    對於
    0.85
    Activations Density 0.009%

    No Known Activations