© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171994
    Prev
    Next
    INDEX
    Explanations

    Slavic, Korean, Arabic script identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    now, now? and talking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    was
    0.47
    rie
    0.46
    TE
    0.45
    ர்ப்ப
    0.45
    ৯৫
    0.44
     IL
    0.43
    รือ
    0.43
     β
    0.43
     STEEL
    0.42
    IE
    0.42
    POSITIVE LOGITS
     sổ
    0.54
    ки
    0.53
     шт
    0.48
     인한
    0.48
    خلي
    0.47
    ския
    0.47
    шт
    0.46
    )}\
    0.45
    ски
    0.44
    дям
    0.44
    Activations Density 0.001%

    No Known Activations