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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8530
    Prev
    Next
    INDEX
    Explanations

    This invention relates to

    np_acts-logits-general · gemini-2.5-flash-lite

    code-related elements such as JavaScript, HTML tags, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    cessive
    -0.75
    لاس
    -0.74
     لم
    -0.73
     Gloss
    -0.71
     dzī
    -0.70
    ⋮
    -0.70
    拍
    -0.70
    illegal
    -0.70
     excessive
    -0.69
    zessin
    -0.69
    POSITIVE LOGITS
    TERM
    0.82
    sze
    0.81
     konsumen
    0.79
    ucun
    0.76
     papaya
    0.75
     musculoskeletal
    0.75
    mus
    0.75
    𝕍
    0.75
     héroes
    0.74
    IDI
    0.74
    Activations Density 0.011%

    No Known Activations