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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8322
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    zept
    -0.77
    监督
    -0.74
    鷹
    -0.66
    伟大
    -0.66
    ego
    -0.65
    egt
    -0.65
    Ал
    -0.65
     烤
    -0.65
    requently
    -0.65
    mok
    -0.64
    POSITIVE LOGITS
     iceberg
    0.69
     Vichy
    0.66
     Imp
    0.65
     Harding
    0.65
    ^@
    0.64
     Typ
    0.64
     cove
    0.63
    Fg
    0.63
     IMPROVEMENT
    0.62
    estudi
    0.61
    Activations Density 0.066%

    No Known Activations