© 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. 57136
    Prev
    Next
    INDEX
    Explanations

    interface elements and structured data

    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
    midrule
    -0.91
     relato
    -0.80
    お疲れ
    -0.80
     està
    -0.75
    }{*}{}
    -0.74
     CASO
    -0.74
    ള്ള
    -0.72
     sesama
    -0.71
    ковник
    -0.71
    parken
    -0.70
    POSITIVE LOGITS
    ,&
    1.02
    =&
    1.00
     &
    0.99
    êtement
    0.93
     Vesta
    0.92
    header
    0.90
     '&
    0.88
    multicolumn
    0.87
     =&
    0.86
    !&
    0.85
    Activations Density 0.003%

    No Known Activations