© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10531
    Prev
    Next
    INDEX
    Explanations

    wood, epoxy, resin crafts

    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
     문제를
    0.48
    Ꮏ
    0.48
    ミュニ
    0.46
    fileExistsAtPath
    0.45
    ㅄ
    0.44
    記者
    0.44
     citizenry
    0.44
     paucity
    0.43
    섦
    0.43
    はどう
    0.43
    POSITIVE LOGITS
     handmade
    1.20
     Handmade
    1.09
     handcrafted
    0.98
    handmade
    0.95
     custom
    0.81
     Etsy
    0.75
     artisan
    0.73
     hand
    0.72
     resin
    0.71
     etsy
    0.70
    Activations Density 0.008%

    No Known Activations