© 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-262K
    7. 109612
    Prev
    Next
    INDEX
    Explanations

    what and why

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    로
    0.55
    ین
    0.54
    し
    0.54
    其他
    0.52
     Después
    0.52
    ש
    0.52
    Akt
    0.50
     estrés
    0.49
    Después
    0.47
    사
    0.46
    POSITIVE LOGITS
    lette
    0.52
    lex
    0.47
    rant
    0.45
    gameOver
    0.45
    ())
    0.45
    igu
    0.44
    lete
    0.44
    getPopulation
    0.44
     BVHTree
    0.43
    getBase
    0.43
    Activations Density 0.002%

    No Known Activations