© 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. 125498
    Prev
    Next
    INDEX
    Explanations

    patterns and methods

    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
     criticizing
    0.52
     criticize
    0.52
     deferred
    0.50
     criticized
    0.48
     slotted
    0.46
     =-
    0.45
     qc
    0.44
     virtual
    0.44
     fclose
    0.43
     (/
    0.43
    POSITIVE LOGITS
     Branches
    0.47
     incarnations
    0.45
     Attitudes
    0.45
     Immigration
    0.45
    Sek
    0.44
    icky
    0.44
     ہے
    0.44
    Chance
    0.43
    诚
    0.43
     Gä
    0.42
    Activations Density 0.001%

    No Known Activations