© 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. 153354
    Prev
    Next
    INDEX
    Explanations

    to sell fast

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

    urethral milk

    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
     воло
    0.52
    retval
    0.50
     丸
    0.49
    </h1>
    0.44
    <0x80>
    0.43
     منزل
    0.43
    begin
    0.42
     modelling
    0.42
     包
    0.42
     листо
    0.42
    POSITIVE LOGITS
    OMET
    0.55
    হি
    0.49
    णिमा
    0.49
    ণ্ট
    0.48
     organiza
    0.48
    羵
    0.48
    Θ
    0.47
    Ⴝ
    0.47
     foes
    0.46
     sulfates
    0.46
    Activations Density 0.001%

    No Known Activations