Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7925
    Prev
    Next
    INDEX
    Explanations

    club or group membership

    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
    বি
    -0.82
     character
    -0.82
     mode
    -0.81
    发
    -0.81
     Bobo
    -0.80
     tissue
    -0.79
    Chart
    -0.78
    Checkbox
    -0.74
     chemical
    -0.74
     sic
    -0.73
    POSITIVE LOGITS
     club
    1.71
     clubs
    1.55
     klub
    1.37
     chapter
    1.33
     members
    1.27
     clube
    1.25
     CLUB
    1.22
    Клуб
    1.21
     membership
    1.20
     chapters
    1.17
    Activations Density 0.066%

    No Known Activations