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. 113
    Prev
    Next
    INDEX
    Explanations

    BIT followed by numbers

    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
     preparar
    -0.79
    {}{}
    -0.75
     painless
    -0.73
    raisals
    -0.71
     preparation
    -0.70
    ároz
    -0.69
     préparation
    -0.68
    blems
    -0.68
     cera
    -0.68
    zwi
    -0.67
    POSITIVE LOGITS
     segíts
    0.80
     hét
    0.77
    enton
    0.77
    поги
    0.77
    ád
    0.75
    Clo
    0.73
    ботинки
    0.73
    NING
    0.73
     içerisinde
    0.72
    itis
    0.71
    Activations Density 0.045%

    No Known Activations