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. 8500
    Prev
    Next
    INDEX
    Explanations

    `int` type declarations

    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
     almost
    -0.90
     más
    -0.90
     nearly
    -0.89
    鶯
    -0.84
     sàng
    -0.82
     even
    -0.82
    باره
    -0.81
    学家
    -0.81
     może
    -0.81
     increased
    -0.79
    POSITIVE LOGITS
     oignons
    0.89
    3
    0.86
    startIndex
    0.84
    随着
    0.84
    隨著
    0.83
     engendered
    0.83
    foque
    0.80
     trente
    0.80
    ιος
    0.80
    レンダー
    0.79
    Activations Density 0.001%

    No Known Activations