© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116192
    Prev
    Next
    INDEX
    Explanations

    Scanner or StandardScaler

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     marijuana
    0.61
     seja
    0.54
    กา
    0.54
    け
    0.53
     в
    0.52
     is
    0.50
    માં
    0.50
     vào
    0.50
     liitty
    0.50
    N
    0.50
    POSITIVE LOGITS
    elden
    0.53
    amsmath
    0.50
    onneur
    0.50
    n
    0.48
     cleanse
    0.48
    ed
    0.48
     এরূপ
    0.48
     جذاب
    0.48
    鏗
    0.48
     রক্ষণ
    0.47
    Activations Density 0.000%

    No Known Activations