© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10981
    Prev
    Next
    INDEX
    Explanations

    automation and filtering

    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_31_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
     (
    0.37
     The
    0.35
     Customer
    0.32
     customers
    0.32
     customer
    0.31
     Tel
    0.31
     یا
    0.30
     Beek
    0.30
     You
    0.30
     özellikle
    0.30
    POSITIVE LOGITS
    п
    0.33
    Ы
    0.32
    ᱙
    0.31
    Extern
    0.31
    brightness
    0.30
    КА
    0.30
     שנה
    0.29
    ז
    0.29
    striatis
    0.29
    ЕР
    0.29
    Activations Density 0.368%

    No Known Activations