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. 8510
    Prev
    Next
    INDEX
    Explanations

    direct-to-consumer businesses

    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
    Vegetation
    -0.85
    jws
    -0.73
    碎片
    -0.72
    厂商
    -0.72
     longstanding
    -0.71
    Prag
    -0.71
     CTE
    -0.71
    eventType
    -0.71
    ्रेस
    -0.69
     Prag
    -0.69
    POSITIVE LOGITS
     DTC
    1.33
    Subscription
    1.06
     subscription
    1.03
     founders
    1.02
     direct
    1.02
    Direct
    1.01
    subscription
    0.96
     Subscription
    0.93
     Direct
    0.92
     subscriptions
    0.92
    Activations Density 0.022%

    No Known Activations