© 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. 84665
    Prev
    Next
    INDEX
    Explanations

    abbreviations starting with SH

    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
    They
    -2.88
    鏨
    -2.70
    ↵
    -2.63
    in
    -2.53
     Также
    -2.39
    ?”
    -2.33
    是非常
    -2.27
    Each
    -2.22
    Possibly
    -2.22
     Not
    -2.20
    POSITIVE LOGITS
    s
    2.98
    玙
    2.78
    𞤢
    2.63
     především
    2.61
    𐬹
    2.52
    哙
    2.42
     ihe
    2.36
     самом
    2.33
     conocen
    2.31
    zení
    2.30
    Activations Density 0.006%

    No Known Activations