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. 119
    Prev
    Next
    INDEX
    Explanations

    Android fill color attributes

    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
    retty
    -0.80
     bodyParser
    -0.74
     ACCIDENT
    -0.73
    tiers
    -0.72
    isesi
    -0.71
    brev
    -0.69
     коле
    -0.68
     voll
    -0.68
    centered
    -0.67
     FISHER
    -0.65
    POSITIVE LOGITS
    iteln
    0.71
    يتر
    0.66
    Different
    0.66
    idp
    0.64
    ഞ്ഞ
    0.64
    不同
    0.64
    tshirt
    0.64
    Freitag
    0.63
    UnitPrice
    0.62
    Sinh
    0.60
    Activations Density 0.065%

    No Known Activations