© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 13626
    Prev
    Next
    INDEX
    Explanations

    frequent, heavy, avid, strong, good users/individuals/consumers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dieu
    0.40
    Tür
    0.38
    ружи
    0.37
     священ
    0.37
    Carr
    0.35
    ccnc
    0.35
    ulz
    0.35
     sacerd
    0.34
    Ä
    0.34
    ización
    0.34
    POSITIVE LOGITS
     learners
    1.59
     drinkers
    1.59
     eaters
    1.57
     thinkers
    1.46
     believers
    1.43
     drinker
    1.43
     thinker
    1.36
     performers
    1.35
     learner
    1.30
     swimmers
    1.27
    Activations Density 0.049%

    No Known Activations