© 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. 10-GEMMASCOPE-RES-131K
    7. 8274
    Prev
    Next
    INDEX
    Explanations

    laying the foundation for

    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_10/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
     aislada
    -1.73
     ممكن
    -1.66
     Dijo
    -1.66
     VERSITY
    -1.66
    ￬
    -1.64
    
    -1.63
     Lagi
    -1.61
    〟
    -1.59
    状态
    -1.58
     seulement
    -1.57
    POSITIVE LOGITS
     for
    2.34
     that
    2.08
     in
    1.70
     quite
    1.57
    </em>
    1.55
     also
    1.54
     regarding
    1.54
    ellido
    1.52
    </h4>
    1.52
    man
    1.52
    Activations Density 0.018%

    No Known Activations