© 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. 211819
    Prev
    Next
    INDEX
    Explanations

    medical or technical terms

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

    positive difference or delta

    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
    0.70
    .'
    0.53
     is
    0.53
    ,'
    0.51
     ,'
    0.51
    ."'
    0.49
     ,"
    0.49
    CELL
    0.49
     Коло
    0.49
     ultimo
    0.48
    POSITIVE LOGITS
    ㄶ
    0.50
    ashions
    0.46
    벍
    0.46
    俳優
    0.46
    買った
    0.46
    モーター
    0.46
    ргә
    0.45
    演技
    0.45
    ᵚ
    0.45
    лә
    0.45
    Activations Density 0.000%

    No Known Activations