© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38969
    Prev
    Next
    INDEX
    Explanations

    Q: and Off

    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_22/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
     but
    -1.48
    髕
    -1.17
    枻
    -1.13
    همان
    -1.11
     comenzado
    -1.11
     eſſ
    -1.07
     escuchado
    -1.06
     broderie
    -1.04
     コットン
    -1.04
    <th>
    -1.04
    POSITIVE LOGITS
     विभिन्न
    1.32
     Entsche
    1.06
     barva
    1.05
    GREES
    1.05
     mert
    1.05
     nyeri
    1.04
    uminense
    1.04
    ónicas
    1.02
    université
    1.01
    lapia
    1.01
    Activations Density 0.001%

    No Known Activations