© 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. 34-GEMMASCOPE-RES-131K
    7. 97970
    Prev
    Next
    INDEX
    Explanations

    extern "C"

    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
    ⅛
    -0.75
     goutte
    -0.74
    茗
    -0.72
    ๒
    -0.72
     Offset
    -0.71
    tiro
    -0.71
    kula
    -0.70
    ⅕
    -0.70
     guarantees
    -0.70
     vacunas
    -0.69
    POSITIVE LOGITS
     export
    1.58
     exported
    1.44
    export
    1.44
    Export
    1.35
     exporting
    1.32
     exports
    1.28
     Export
    1.28
     EXPORT
    1.18
     exportation
    1.16
    导出
    1.13
    Activations Density 0.045%

    No Known Activations