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. 8613
    Prev
    Next
    INDEX
    Explanations

    code annotations and nullability

    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
    יני
    -0.78
     extré
    -0.77
     salade
    -0.72
     فض
    -0.71
    peated
    -0.71
    烈
    -0.70
    であった
    -0.69
     Louvain
    -0.69
     Namespace
    -0.68
     herbes
    -0.68
    POSITIVE LOGITS
    lom
    0.94
     annotations
    0.94
     annotation
    0.88
    Since
    0.86
     races
    0.83
     incub
    0.81
    kirche
    0.81
     jspb
    0.81
     suun
    0.81
     SPC
    0.80
    Activations Density 0.028%

    No Known Activations