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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7774
    Prev
    Next
    INDEX
    Explanations

    stadiums and their capacity

    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
     called
    -0.77
    厦
    -0.73
    ادل
    -0.72
     humour
    -0.72
    language
    -0.71
     hayas
    -0.69
    prog
    -0.69
     Fellowships
    -0.68
    bigskip
    -0.68
     triggered
    -0.67
    POSITIVE LOGITS
     stadium
    1.18
    🏟
    0.99
    stadium
    0.98
     synthetic
    0.92
     astro
    0.90
     stadiums
    0.90
     Stadium
    0.88
    acyjnych
    0.84
     Capacity
    0.82
    capacity
    0.80
    Activations Density 0.032%

    No Known Activations