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. 8438
    Prev
    Next
    INDEX
    Explanations

    legal precedent and case citations

    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
    ;?>
    -0.83
    StandardCharsets
    -0.75
    尽快
    -0.73
     ули
    -0.73
     парка
    -0.71
     Goku
    -0.70
    ваемых
    -0.69
     Fad
    -0.68
     najbolj
    -0.68
    铂
    -0.68
    POSITIVE LOGITS
     cases
    3.23
     case
    2.34
    cases
    2.31
    Cases
    2.28
     Cases
    2.19
     authorities
    2.05
     decisions
    1.94
     authority
    1.90
     CASES
    1.73
     casos
    1.68
    Activations Density 0.093%

    No Known Activations