© 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-16K
    7. 6480
    Prev
    Next
    INDEX
    Explanations

    lisp, clojure, mathematica, programming

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    arat
    0.45
     Atth
    0.44
    อกจาก
    0.43
     همچنین
    0.43
    鲮
    0.43
    imaan
    0.41
     אתה
    0.41
     अलावा
    0.40
     मारने
    0.39
    arati
    0.39
    POSITIVE LOGITS
    瑋
    0.43
    ୋ
    0.42
     referenties
    0.41
     audiences
    0.41
    ވަ
    0.40
    ੌਰ
    0.39
    ных
    0.39
     faveur
    0.39
    водство
    0.39
     hoofdst
    0.39
    Activations Density 0.036%

    No Known Activations