© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    android and python imports

    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
     pytest
    0.44
     criteri
    0.43
    гыз
    0.43
     smatra
    0.43
     hydroxide
    0.42
    甾
    0.42
     फ़रवरी
    0.41
    স্তি
    0.40
     ಯಾವುದ
    0.40
    StateException
    0.40
    POSITIVE LOGITS
    confirmation
    0.44
     آتش
    0.40
    を中心に
    0.40
    顶
    0.39
     кноп
    0.37
    Confirm
    0.37
     toolbar
    0.36
    $('.
    0.34
    ケ
    0.34
    コン
    0.34
    Activations Density 0.003%

    No Known Activations