© 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. 186956
    Prev
    Next
    INDEX
    Explanations

    linked to, release slowly, traveling back

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

    technical jargon

    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
    пло
    0.50
     вещества
    0.49
    вер
    0.49
    va
    0.47
     inay
    0.46
     категория
    0.45
    лет
    0.45
    烬
    0.43
    𝟐
    0.43
    )=-\
    0.43
    POSITIVE LOGITS
     Several
    0.51
     Adopt
    0.49
     Disco
    0.48
     Interpre
    0.48
     Transl
    0.47
     tunes
    0.47
     automobiles
    0.46
     interpre
    0.46
     sys
    0.46
     Buen
    0.45
    Activations Density 0.000%

    No Known Activations