© 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. 247056
    Prev
    Next
    INDEX
    Explanations

    organized, carb, photo, loss

    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
    kst
    0.48
     συγκ
    0.48
    訫
    0.46
     منسل
    0.45
     రావ
    0.45
     गुंतवणूक
    0.45
    들아
    0.45
     intimated
    0.44
    忶
    0.44
     దగ్
    0.43
    POSITIVE LOGITS
     adult
    0.50
    (
    0.50
    System
    0.46
    t
    0.46
     ad
    0.46
     Hao
    0.45
     panneau
    0.45
     część
    0.45
    L
    0.44
     video
    0.44
    Activations Density 0.000%

    No Known Activations