© 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. 170033
    Prev
    Next
    INDEX
    Explanations

    lists of numbers or points

    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
    presso
    0.46
    sker
    0.45
    removeAll
    0.44
    dependencies
    0.44
    bilt
    0.43
    userInfo
    0.43
    signing
    0.43
    ग
    0.43
    basis
    0.43
    saya
    0.43
    POSITIVE LOGITS
     trombone
    0.46
     Quiz
    0.43
     μέρος
    0.43
     milliards
    0.42
     коды
    0.42
    !
    0.41
     Почему
    0.41
     Jokes
    0.41
     що
    0.41
     лига
    0.41
    Activations Density 0.000%

    No Known Activations