© 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-65K
    7. 47721
    Prev
    Next
    INDEX
    Explanations

    code or markup snippets<end_of_turn><start_of_turn>

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ;
    0.46
     ؛
    0.43
     respectively
    0.41
     ;;
    0.40
     respectiv
    0.40
    respectively
    0.40
    分別
    0.38
     ;{
    0.38
    *_
    0.37
    𝘭
    0.37
    POSITIVE LOGITS
     hazır
    0.41
     benar
    0.39
     kê
    0.38
     Podczas
    0.38
    ného
    0.38
     krem
    0.37
     акысыз
    0.35
    जेंट
    0.35
     Wirk
    0.35
     sich
    0.35
    Activations Density 0.072%

    No Known Activations