© 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. 239826
    Prev
    Next
    INDEX
    Explanations

    screen or organs

    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
    a
    0.73
    m
    0.53
    া
    0.50
    w
    0.49
    i
    0.49
    dah
    0.48
    sites
    0.48
    suff
    0.48
    dac
    0.46
    s
    0.46
    POSITIVE LOGITS
     スク
    0.52
     órganos
    0.52
     schermo
    0.51
     organes
    0.51
     ganador
    0.50
     chari
    0.49
     écran
    0.49
     wskaz
    0.49
     cardiaque
    0.48
     tagReport
    0.48
    Activations Density 0.000%

    No Known Activations