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. 89
    Prev
    Next
    INDEX
    Explanations

    heraldic symbols and emblems

    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
    documentclass
    -0.78
    INATION
    -0.73
     István
    -0.72
     سک
    -0.71
     IPC
    -0.70
     المنتج
    -0.69
     Becky
    -0.69
     Everett
    -0.69
    }^{-
    -0.69
    mkdir
    -0.69
    POSITIVE LOGITS
     crest
    2.55
     coat
    2.47
     Coat
    2.39
    Coat
    2.06
     Crest
    2.02
    crest
    1.94
    Crest
    1.87
     shield
    1.84
     arms
    1.84
     coats
    1.78
    Activations Density 0.072%

    No Known Activations