© 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. 80771
    Prev
    Next
    INDEX
    Explanations

    about followed by a number or word

    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
     deserves
    0.53
    roits
    0.49
     earnestly
    0.48
     equating
    0.47
    yczny
    0.47
    crumbs
    0.46
     conceding
    0.46
     ആ
    0.45
     창
    0.45
     iki
    0.45
    POSITIVE LOGITS
    ны
    0.54
    。
    0.45
     vuelo
    0.44
    故意
    0.44
    色
    0.44
    до
    0.44
    肉
    0.43
    被
    0.42
    颜色
    0.41
    調
    0.41
    Activations Density 0.001%

    No Known Activations