© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99772
    Prev
    Next
    INDEX
    Explanations

    know [degree] about

    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
    〼
    -1.73
    
    -1.73
     kön
    -1.66
    铙
    -1.63
    🕗
    -1.62
     "}
    -1.59
     knapp
    -1.56
     vielleicht
    -1.56
     reclama
    -1.55
    Zubereitung
    -1.55
    POSITIVE LOGITS
     about
    2.91
     of
    2.73
     from
    2.39
     on
    2.11
    ();
    1.65
    C
    1.63
     beziehungs
    1.54
    6
    1.53
     than
    1.52
     miliardi
    1.52
    Activations Density 0.022%

    No Known Activations