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. 8502
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
     diário
    -0.69
     continue
    -0.69
     primes
    -0.67
    oriasis
    -0.65
    дій
    -0.63
     Cen
    -0.63
    ่วม
    -0.63
    )}$,
    -0.63
    ьет
    -0.63
     could
    -0.63
    POSITIVE LOGITS
    大利
    0.71
    setEditable
    0.69
    UNIVERSITY
    0.67
     Futsal
    0.65
    help
    0.65
    VERT
    0.65
    ማ
    0.65
    unk
    0.65
    mua
    0.65
    cshtml
    0.64
    Activations Density 0.060%

    No Known Activations