© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8275
    Prev
    Next
    INDEX
    Explanations

    parentheses in math and code

    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_65k_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
     Moira
    0.37
    赈
    0.36
    ńskim
    0.35
    营业
    0.34
    物资
    0.34
    獒
    0.33
    货币
    0.32
    гыз
    0.32
    Coal
    0.32
    ოლი
    0.32
    POSITIVE LOGITS
     equations
    0.44
     に
    0.39
    equations
    0.37
     ?
    0.36
     topology
    0.36
     Equations
    0.36
     subroutine
    0.36
     math
    0.36
     stoichiometry
    0.35
     equation
    0.35
    Activations Density 0.020%

    No Known Activations