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. 8101
    Prev
    Next
    INDEX
    Explanations

    reads or stated text

    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
    HEIM
    -0.83
    Źródło
    -0.79
    inaire
    -0.73
    Tell
    -0.71
    ğun
    -0.71
     рассказыва
    -0.70
     września
    -0.69
    SourceChecksum
    -0.69
    κά
    -0.69
    cises
    -0.68
    POSITIVE LOGITS
     reads
    5.00
     read
    4.13
    reads
    3.45
     Reads
    3.19
    Reads
    2.94
    read
    2.80
     reading
    2.77
    读
    2.38
     READ
    2.25
     readings
    2.14
    Activations Density 0.046%

    No Known Activations