© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61082
    Prev
    Next
    INDEX
    Explanations

    Insurance, compared, teaches, land, toxic

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    deviation
    0.53
    いっぱい
    0.51
    亍
    0.47
    entering
    0.47
    conductivity
    0.46
    เพื่อ
    0.45
    绁
    0.44
    два
    0.43
    dimensionality
    0.43
    치
    0.43
    POSITIVE LOGITS
     U
    0.48
     weiterhin
    0.46
     ques
    0.45
    IAL
    0.45
    ILY
    0.45
     negras
    0.44
     sección
    0.44
     pós
    0.44
    ird
    0.43
     Nationals
    0.43
    Activations Density 0.021%

    No Known Activations