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. 8141
    Prev
    Next
    INDEX
    Explanations

    sports teams and collectibles

    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
    TokenNameEQUAL
    -0.86
     humanos
    -0.85
     INSPIRE
    -0.74
     screenshots
    -0.69
    ンダル
    -0.69
    Согласно
    -0.69
    jectures
    -0.68
    埃及
    -0.68
     pata
    -0.67
     malfunction
    -0.66
    POSITIVE LOGITS
     cards
    1.01
     card
    0.96
     Pose
    0.85
     backs
    0.84
     tobacco
    0.81
     poses
    0.81
    Pose
    0.80
    expressions
    0.80
    HORIZONTAL
    0.80
     borders
    0.79
    Activations Density 0.006%

    No Known Activations