© 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. 113015
    Prev
    Next
    INDEX
    Explanations

    account identifiers

    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
     ;\
    0.44
    Основные
    0.44
    ין
    0.43
     nachhalt
    0.43
    勰
    0.43
    ješt
    0.43
     الانسان
    0.42
     പഠ
    0.41
    ән
    0.41
    鐩
    0.41
    POSITIVE LOGITS
    сить
    0.50
    ного
    0.48
     quickly
    0.47
    (
    0.47
     I
    0.47
     nozzle
    0.46
    )->
    0.45
     It
    0.44
     That
    0.44
     faucet
    0.43
    Activations Density 0.002%

    No Known Activations