© 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. 31113
    Prev
    Next
    INDEX
    Explanations

    programming imports and declarations

    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
     during
    -0.97
     μπορεί
    -0.94
    nější
    -0.90
     out
    -0.88
     steigen
    -0.88
    舆
    -0.86
    ناق
    -0.86
     pán
    -0.86
     today
    -0.83
    yyv
    -0.82
    POSITIVE LOGITS
     haja
    0.98
    kai
    0.92
     λ
    0.88
    踉
    0.88
    Sursa
    0.87
     Tt
    0.85
    怎么了
    0.85
    niak
    0.85
    : 
    0.85
     auparavant
    0.83
    Activations Density 0.042%

    No Known Activations