© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177085
    Prev
    Next
    INDEX
    Explanations

    Excel templates

    np_acts-logits-general · gemini-2.5-flash-lite

    improve retrieval performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AL
    0.57
     Jesuits
    0.53
     Tets
    0.50
    鮎
    0.48
     RCMP
    0.48
     EET
    0.47
     paymentRequest
    0.47
     יש
    0.47
     racemic
    0.45
     विवेकानंद
    0.45
    POSITIVE LOGITS
    삭제
    0.50
    cleaned
    0.48
    Folder
    0.45
    Middleware
    0.45
     మాత్ర
    0.44
    Collectors
    0.44
    存
    0.44
    aná
    0.44
    作物
    0.43
    Serialize
    0.43
    Activations Density 0.000%

    No Known Activations