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. 8081
    Prev
    Next
    INDEX
    Explanations

    referencing documentation or sources

    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
    itunes
    -0.96
    任何人
    -0.91
    痪
    -0.90
     resume
    -0.88
    VIAF
    -0.87
    comcast
    -0.85
    ченко
    -0.85
     weiterhin
    -0.85
    CRIPTION
    -0.84
    чехол
    -0.84
    POSITIVE LOGITS
    官方
    1.38
     documentation
    1.37
     here
    1.36
     officiel
    1.31
     official
    1.23
     https
    1.15
    stackoverflow
    1.14
     How
    1.13
     MSD
    1.10
     documentación
    1.07
    Activations Density 0.286%

    No Known Activations