© 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. 38729
    Prev
    Next
    INDEX
    Explanations

    URLs to news and articles

    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
    MongoDB
    -1.80
     âges
    -1.74
    聼
    -1.72
    </em>
    -1.70
     itinéraires
    -1.63
    ——”
    -1.56
    拶
    -1.54
    熵
    -1.54
    眸
    -1.51
     vader
    -1.48
    POSITIVE LOGITS
     the
    1.95
    谁能
    1.52
     each
    1.41
    叭
    1.40
     loosing
    1.38
    SaveChangesAsync
    1.36
    越是
    1.33
    为什么会
    1.28
     will
    1.27
    ’
    1.27
    Activations Density 0.080%

    No Known Activations