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. 8148
    Prev
    Next
    INDEX
    Explanations

    % modulo operations and string formatting

    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
    WindowConstants
    -0.79
    jena
    -0.75
     Margar
    -0.70
    älde
    -0.69
    чера
    -0.68
     望
    -0.68
    ''',
    -0.68
    "><?=
    -0.68
     cem
    -0.67
    "><?
    -0.67
    POSITIVE LOGITS
     %
    3.91
    %
    3.55
     \%
    2.52
    ()%
    2.36
     $\%
    2.27
    \%
    2.20
     $\%$
    2.17
     modulo
    2.14
     mod
    2.06
     %=
    2.06
    Activations Density 0.118%

    No Known Activations