© 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. 153208
    Prev
    Next
    INDEX
    Explanations

    specific nouns and follow-ups

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

    mild, mini, policy, encourages

    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
    🛖
    0.55
    Ნ
    0.53
    ΡΑ
    0.51
    ﻦ
    0.48
    бора
    0.47
    ้ํา
    0.47
    ność
    0.47
    壹百
    0.47
    十几
    0.47
    𝖊
    0.47
    POSITIVE LOGITS
                   
    0.54
     (
    0.50
    O
    0.49
     ;
    0.47
     ,
    0.47
    Time
    0.45
    Id
    0.44
    t
    0.44
    c
    0.44
    red
    0.43
    Activations Density 0.000%

    No Known Activations