© 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. 22-GEMMASCOPE-RES-131K
    7. 34149
    Prev
    Next
    INDEX
    Explanations

    groove, Grove, glove, gloves

    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
    豨
    -3.08
    elernt
    -3.06
    意味着
    -3.02
    齷
    -2.78
    诳
    -2.75
    ᎑
    -2.66
     betreffenden
    -2.58
    at
    -2.56
    髡
    -2.52
    グルト
    -2.45
    POSITIVE LOGITS
     of
    4.47
     और
    3.14
     și
    3.00
    ;
    2.94
     и
    2.75
     và
    2.72
     και
    2.59
    ’
    2.55
    —
    2.53
    ,"
    2.50
    Activations Density 0.015%

    No Known Activations