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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7276
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
     Hesap
    0.36
    oretically
    0.36
    韫
    0.36
    WallArray
    0.35
     logique
    0.35
    Listo
    0.34
     écoul
    0.34
    蓣
    0.33
    verständlich
    0.33
    媺
    0.33
    POSITIVE LOGITS
    based
    0.39
    gras
    0.36
    PA
    0.35
    CHD
    0.34
    Canada
    0.34
     université
    0.34
    GOLD
    0.34
    core
    0.33
    JA
    0.33
    east
    0.33
    Activations Density 0.139%

    No Known Activations