© 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. 21750
    Prev
    Next
    INDEX
    Explanations

    or different languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    單
    0.42
     uses
    0.41
    бата
    0.40
    ieved
    0.40
    のみ
    0.39
     использовании
    0.38
    ிய
    0.38
    饌
    0.38
    コスト
    0.38
     ફક્ત
    0.38
    POSITIVE LOGITS
     atau
    0.59
     hoặc
    0.58
     किंवा
    0.57
     أو
    0.56
     அல்லது
    0.56
     vagy
    0.54
     অথবা
    0.54
     কিংবা
    0.53
     või
    0.52
     eller
    0.52
    Activations Density 0.001%

    No Known Activations