© 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. 173940
    Prev
    Next
    INDEX
    Explanations

    by

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

    give you a list

    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
    eng
    0.57
    ans
    0.48
    '
    0.48
    ana
    0.46
    anaa
    0.45
    acu
    0.44
    etur
    0.43
    aku
    0.43
    aj
    0.43
    ik
    0.43
    POSITIVE LOGITS
    URNIZ
    0.56
    ﻔ
    0.54
    ﺨ
    0.53
     Colombeau
    0.52
     testicule
    0.52
    チップ
    0.52
     argumentos
    0.51
     vortices
    0.50
     mischievous
    0.49
    ﺧ
    0.48
    Activations Density 0.000%

    No Known Activations