© 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. 56740
    Prev
    Next
    INDEX
    Explanations

    understanding appreciating fight

    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
    ടിച്ച
    0.44
     Maths
    0.43
     бясплатна
    0.43
     Découvrez
    0.42
     لیون
    0.41
    ეგისტრ
    0.41
    วา
    0.41
     Datei
    0.41
    袄
    0.40
     สืบค้นเมื่อ
    0.40
    POSITIVE LOGITS
    ROTATE
    0.47
     precipit
    0.46
    다
    0.44
    pentine
    0.43
     hoof
    0.42
    ниць
    0.42
    rett
    0.42
    лоти
    0.42
     ör
    0.41
     initiate
    0.41
    Activations Density 0.007%

    No Known Activations