© 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. 30023
    Prev
    Next
    INDEX
    Explanations

    detailed explanation of how

    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
     virulent
    0.51
     insidious
    0.45
     intelligents
    0.45
    掻
    0.44
     disillusion
    0.44
     disconcert
    0.44
    ⤷
    0.44
     людей
    0.43
    ucionales
    0.43
     paranoid
    0.42
    POSITIVE LOGITS
    هرة
    0.52
     advancements
    0.50
     efforts
    0.47
    の為
    0.46
     actions
    0.45
    将会
    0.45
     التأ
    0.44
     tributes
    0.44
     payment
    0.43
     为
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.