© 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. 100371
    Prev
    Next
    INDEX
    Explanations

    groups, buffer, season, listing, pool, franchises, collection, set, sequences, line

    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
    providedIn
    -1.81
    ["
    -1.45
     対策
    -1.38
    ÁND
    -1.38
    ।
    -1.34
     "
    -1.31
    。
    -1.30
    they
    -1.30
     certain
    -1.28
    say
    -1.27
    POSITIVE LOGITS
     când
    1.43
     которые
    1.35
    nischen
    1.33
     novembro
    1.30
    
    1.29
    蚨
    1.28
    autorisation
    1.27
    ㄋ
    1.25
    okkal
    1.23
     zdol
    1.23
    Activations Density 0.375%

    No Known Activations