© 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. 153326
    Prev
    Next
    INDEX
    Explanations

    Specific word sequences

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

    similarities, complexity, feeling, place

    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
    शिलाजीत
    0.51
     industrialists
    0.51
    ndan
    0.47
    쇤
    0.47
     देहरादून
    0.45
    媑
    0.45
    も
    0.44
    婫
    0.44
    функ
    0.44
    न्दावन
    0.44
    POSITIVE LOGITS
    0.53
     समझा
    0.45
    <0xEF>
    0.45
     rong
    0.45
    ot
    0.43
     English
    0.43
     duel
    0.42
     Ao
    0.40
     Tart
    0.40
     Engl
    0.40
    Activations Density 0.000%

    No Known Activations