© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14367
    Prev
    Next
    INDEX
    Explanations

    module require

    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_40_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
    Unary
    0.41
    𝙼
    0.40
    NUM
    0.38
     Kurz
    0.37
    䉼
    0.37
     जेब
    0.37
     stuffed
    0.37
    boundingRect
    0.36
    ྫ
    0.36
     speciality
    0.36
    POSITIVE LOGITS
     require
    1.71
    require
    1.65
     Require
    1.52
    Require
    1.44
     requiring
    1.26
     requires
    1.19
     REQUIRE
    1.19
     requieren
    1.13
     requiere
    1.09
     requer
    1.07
    Activations Density 0.007%

    No Known Activations