© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    forms, structures, and abstract concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝗹
    0.41
    ο
    0.40
    기
    0.39
     Polymer
    0.39
     thei
    0.39
     reproductive
    0.39
    τή
    0.38
     kimia
    0.38
    ง
    0.38
    व
    0.38
    POSITIVE LOGITS
    ’
    0.67
    A
    0.57
    től
    0.56
     மீண்டும்
    0.56
     ನಲ್ಲಿ
    0.54
    ot
    0.54
    ِّف
    0.53
    ’;
    0.53
    lauf
    0.52
    nimmt
    0.52
    Activations Density 0.331%

    No Known Activations