© 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. 129598
    Prev
    Next
    INDEX
    Explanations

    landfill for, Monday on, to prepare

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

    smell of, option 1

    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
     cuarta
    0.52
    ुर्
    0.51
    ﻱ
    0.49
    numero
    0.48
    зулта
    0.48
     телефо
    0.48
    フラワー
    0.47
    проце
    0.47
    ೪
    0.47
    ﻕ
    0.46
    POSITIVE LOGITS
     Single
    0.49
    Single
    0.47
     single
    0.46
     ฉ
    0.45
     Track
    0.43
    单一
    0.42
    ↵↵
    0.41
     Bundesliga
    0.40
    ys
    0.40
     Preservation
    0.40
    Activations Density 0.001%

    No Known Activations