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. 7841
    Prev
    Next
    INDEX
    Explanations

    equity capital, share, market

    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
     Importantly
    -0.92
    已然
    -0.90
     按
    -0.83
    人不
    -0.83
    망
    -0.82
     особы
    -0.82
     Know
    -0.81
     =
    -0.80
     Notably
    -0.80
    <u>
    -0.79
    POSITIVE LOGITS
     ГА
    1.02
    gericht
    1.02
     minded
    0.99
    ternut
    0.98
    ckeye
    0.98
     durumu
    0.96
    зія
    0.96
     crowdfunding
    0.95
     peinado
    0.93
    iciens
    0.93
    Activations Density 0.008%

    No Known Activations