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. 7823
    Prev
    Next
    INDEX
    Explanations

    Electoral Deputy Henry Octa

    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
    trees
    -0.82
    購
    -0.73
    韓
    -0.72
    フォト
    -0.71
     Checklist
    -0.71
    Theta
    -0.71
    ሮ
    -0.69
    肯
    -0.69
    陽
    -0.69
    oree
    -0.69
    POSITIVE LOGITS
    umą
    0.77
     embarazadas
    0.75
     [-
    0.71
    撸
    0.68
     Kli
    0.68
    ocytic
    0.68
     ACR
    0.68
     sailor
    0.68
    cker
    0.67
     Bros
    0.66
    Activations Density 0.023%

    No Known Activations