© 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-262K
    7. 54932
    Prev
    Next
    INDEX
    Explanations

    fiddling or repetitive actions

    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_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
     ஈ
    0.37
     tendrás
    0.37
     EFI
    0.36
     благодаря
    0.36
    ênh
    0.36
     shout
    0.35
    öpf
    0.35
     Xác
    0.35
    輝
    0.35
     denunci
    0.34
    POSITIVE LOGITS
     fidget
    0.82
     doodles
    0.50
    entretien
    0.50
     mindless
    0.46
    掑
    0.46
     cigarettes
    0.46
     dood
    0.46
    闲
    0.46
     fiddle
    0.46
     idle
    0.45
    Activations Density 0.054%

    No Known Activations