© 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. 129021
    Prev
    Next
    INDEX
    Explanations

    types and kinds

    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
    ut
    0.57
    ድረግ
    0.53
    b
    0.52
    a
    0.51
    લ
    0.50
     ഒരിക്ക
    0.50
    z
    0.49
    fung
    0.49
    嶈
    0.49
    ス
    0.48
    POSITIVE LOGITS
     చక్క
    0.45
    Jenis
    0.44
     انواع
    0.42
    hasa
    0.42
    えられる
    0.42
    ेलकम
    0.40
    نوع
    0.39
    ombasa
    0.39
     रचना
    0.39
     литератур
    0.38
    Activations Density 0.001%

    No Known Activations