© 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. 40-GEMMASCOPE-2-RES-262K
    7. 611
    Prev
    Next
    INDEX
    Explanations

    barely acknowledged or not

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ük
    0.42
    利用
    0.42
     الفر
    0.40
     majoring
    0.39
     sidelined
    0.39
     ब्रैकेट
    0.39
     Unfortunately
    0.37
     неболь
    0.37
    <sub>
    0.36
    dependent
    0.36
    POSITIVE LOGITS
     siquiera
    0.74
     coher
    0.67
     coherent
    0.63
     explicação
    0.55
     consciously
    0.54
    表情
    0.50
     fysis
    0.49
     Worte
    0.49
     comprehend
    0.48
     woorden
    0.48
    Activations Density 0.041%

    No Known Activations