© 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. 84430
    Prev
    Next
    INDEX
    Explanations

    spreading information or ideas

    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
    𐐪
    -2.06
    ми
    -1.93
    ⢪
    -1.84
    "—
    -1.76
    されていない
    -1.74
     abiertos
    -1.72
     cocinas
    -1.72
    _
    -1.71
     mystery
    -1.70
     ون
    -1.70
    POSITIVE LOGITS
    ,”
    2.56
     unſ
    2.41
    ftrag
    1.98
    ︓
    1.85
    疍
    1.80
    ;
    1.80
     eivät
    1.77
     Keine
    1.77
    ↀ
    1.76
    ⃢
    1.74
    Activations Density 0.006%

    No Known Activations