© 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. 24763
    Prev
    Next
    INDEX
    Explanations

    technical commands and code

    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
     consec
    0.44
    住了
    0.43
     lighted
    0.42
     scopo
    0.42
     ब्रह्मा
    0.41
     crema
    0.40
    Apakah
    0.39
     molte
    0.38
    珐
    0.38
     candidatura
    0.38
    POSITIVE LOGITS
    "};
    0.48
     όλ
    0.44
    ores
    0.44
    \;
    0.44
    㶱
    0.43
    asiti
    0.43
    ทั้งหมด
    0.42
    '))->
    0.42
     بلد
    0.42
    erit
    0.42
    Activations Density 0.004%

    No Known Activations