Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8346
    Prev
    Next
    INDEX
    Explanations

    programmatic type access

    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_34/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
    før
    -0.90
     Coupé
    -0.90
     kimdir
    -0.89
    TableViewCell
    -0.80
    ବ
    -0.78
    Economía
    -0.78
     oj
    -0.77
    疱
    -0.77
     COVER
    -0.76
    ')))
    -0.76
    POSITIVE LOGITS
     typeof
    0.86
    typeof
    0.81
    cipes
    0.78
    嬿
    0.77
    盒
    0.76
     mengandung
    0.73
     kubwa
    0.73
    明日は
    0.73
     spartan
    0.73
    estres
    0.73
    Activations Density 0.008%

    No Known Activations