© 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. 103518
    Prev
    Next
    INDEX
    Explanations

    design and reports

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

    speech recognition and response

    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
     ё
    0.52
    は
    0.52
     県
    0.52
     растение
    0.51
     являются
    0.51
     губерна
    0.49
     याद
    0.49
     липня
    0.49
     коэффициент
    0.49
     охорони
    0.48
    POSITIVE LOGITS
    ر
    0.48
     elders
    0.46
    خ
    0.44
    טו
    0.44
     Elders
    0.43
    تو
    0.43
    يّ
    0.42
    লায়
    0.41
     Seaside
    0.41
    ي
    0.41
    Activations Density 0.001%

    No Known Activations