© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114046
    Prev
    Next
    INDEX
    Explanations

    second piece

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

    ensembles, reduction, chamber, struct

    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
    Negative Logits
    沚
    0.52
     debugShow
    0.52
     класса
    0.50
    శ
    0.49
    毓
    0.49
    Х
    0.48
    Со
    0.47
     المش
    0.47
    瀏
    0.47
     مش
    0.46
    POSITIVE LOGITS
     remarkably
    0.50
    alto
    0.46
    ta
    0.46
    wagon
    0.46
     tucked
    0.45
    té
    0.45
    issant
    0.45
    vase
    0.44
    umbre
    0.44
    uppe
    0.44
    Activations Density 0.001%

    No Known Activations