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. 8309
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
     plage
    -0.75
     COVER
    -0.71
     moy
    -0.71
    Cn
    -0.71
     NSP
    -0.71
     contenedores
    -0.70
    Cal
    -0.69
     appropriation
    -0.69
     Rolf
    -0.69
     Haye
    -0.69
    POSITIVE LOGITS
     Stephen
    1.14
    Stephen
    0.96
     into
    0.89
     Sweeney
    0.87
     Into
    0.84
    osse
    0.73
    ondheim
    0.72
     Giud
    0.70
    侯
    0.69
    Into
    0.69
    Activations Density 0.032%

    No Known Activations