© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE TABLE

    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
     paisajes
    0.43
     crossbody
    0.42
    蒐
    0.40
     paisaje
    0.40
     dupatta
    0.40
     searchValue
    0.40
     straw
    0.39
     xyl
    0.39
    ᡧ
    0.39
     rocking
    0.39
    POSITIVE LOGITS
    CreateTable
    1.20
    CREATE
    1.07
     CREATE
    1.05
    创建
    0.96
    Create
    0.93
     migrations
    0.92
     creation
    0.90
    Migration
    0.90
     create
    0.89
     Create
    0.89
    Activations Density 0.024%

    No Known Activations