© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31629
    Prev
    Next
    INDEX
    Explanations

    code components and syntax

    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
     [];
    -1.05
    ;
    -1.02
     كات
    -1.00
    cet
    -0.84
     [];
    
    -0.84
     ['
    -0.84
    わから
    -0.83
     después
    -0.83
    分から
    -0.82
    就不会
    -0.82
    POSITIVE LOGITS
    (
    
    1.19
    ()),
    1.19
     lære
    1.04
     bascul
    1.00
     nivå
    0.98
     olje
    0.97
     tissus
    0.97
     réinitial
    0.96
    )$,
    0.95
    audiovisuel
    0.93
    Activations Density 0.001%

    No Known Activations