© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54932
    Prev
    Next
    INDEX
    Explanations

    idle or repetitive actions

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ஈ
    0.42
     celebración
    0.40
    ênh
    0.40
     überras
    0.39
    Fernando
    0.39
     রেফার
    0.39
     anuncia
    0.38
    Gracias
    0.37
     denunci
    0.37
    輝
    0.36
    POSITIVE LOGITS
     fidget
    0.95
     doodles
    0.63
     daydream
    0.53
     chewing
    0.52
     fiddle
    0.52
     dood
    0.51
     tinker
    0.51
     snacking
    0.50
     cigarette
    0.49
    hile
    0.48
    Activations Density 0.031%

    No Known Activations