© 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. 63658
    Prev
    Next
    INDEX
    Explanations

    exceptional care

    np_acts-logits-general · gemini-2.5-flash-lite

    code configuration and logging

    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
    i
    0.51
    oline
    0.46
     N
    0.46
     vise
    0.45
     stek
    0.45
    weiser
    0.44
    ra
    0.44
    ND
    0.44
     flattering
    0.43
    N
    0.43
    POSITIVE LOGITS
    ப்புகளில்
    0.51
     ক্ষুধার
    0.48
     मतदारसंघात
    0.48
     પ્રથમ
    0.47
     кеңселер
    0.47
     ಅನುಪಾತ
    0.45
    ப்பும்
    0.45
     поддер
    0.45
    單位
    0.44
    বছর
    0.44
    Activations Density 0.000%

    No Known Activations