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. 8411
    Prev
    Next
    INDEX
    Explanations

    rights to

    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
     even
    -1.08
     especially
    -1.07
     not
    -1.04
     vicin
    -1.03
     first
    -0.98
     huwa
    -0.97
     secretly
    -0.96
     only
    -0.95
    配慮
    -0.91
     how
    -0.91
    POSITIVE LOGITS
    ❯
    1.03
     trám
    0.91
    Similar
    0.91
    —¡
    0.88
     Auflösung
    0.87
     Estas
    0.86
     két
    0.85
    lý
    0.85
     Posteriormente
    0.85
    asily
    0.83
    Activations Density 0.004%

    No Known Activations