© 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. 179937
    Prev
    Next
    INDEX
    Explanations

    visiting placeholder pages

    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
    謦
    0.47
     युग
    0.46
    рд
    0.46
    ጥር
    0.45
    ರ್‌
    0.44
     الكبير
    0.44
    便是
    0.44
     সমস্যার
    0.43
    cretion
    0.43
    eynman
    0.42
    POSITIVE LOGITS
    v
    0.51
    nite
    0.50
    s
    0.45
     Edwards
    0.44
     jol
    0.44
     Exel
    0.43
    dde
    0.43
    a
    0.43
     photos
    0.42
     aks
    0.42
    Activations Density 0.000%

    No Known Activations