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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 16783
    Prev
    Next
    INDEX
    Explanations

    positive evaluations of features and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     याची
    0.40
     每个
    0.38
     मोटा
    0.38
     diferenças
    0.37
    虚
    0.37
    rets
    0.35
     действий
    0.34
    なくな
    0.33
     prettier
    0.32
    ၃
    0.32
    POSITIVE LOGITS
     documentation
    0.67
     Documentation
    0.53
     support
    0.50
    documentation
    0.48
     reputation
    0.47
     acoustics
    0.45
     finances
    0.45
    Documentation
    0.44
     documentación
    0.44
     ventilation
    0.44
    Activations Density 0.014%

    No Known Activations