© 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. 90935
    Prev
    Next
    INDEX
    Explanations

    actions and statements

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

    exploring possibilities

    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
     végétaux
    0.51
     vegetal
    0.50
     conscientes
    0.47
     consciente
    0.47
    ﻔ
    0.47
    Restriction
    0.45
    誹
    0.44
     pés
    0.44
    zech
    0.43
     seizure
    0.43
    POSITIVE LOGITS
     시간을
    0.54
    时间
    0.54
    시간
    0.51
     시간
    0.49
    8
    0.49
    antemente
    0.48
    虱
    0.47
    人力
    0.47
     Camping
    0.46
     Outreach
    0.46
    Activations Density 0.000%

    No Known Activations