© 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. 147754
    Prev
    Next
    INDEX
    Explanations

    study of, name has

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

    knew when. fine when. division with

    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
    Not in Any Lists

    No Comments

    Negative Logits
    妛
    0.51
    ymmetries
    0.48
    Nä
    0.46
    GoString
    0.45
     फास्ट
    0.44
    واع
    0.44
    Seoul
    0.44
    酘
    0.43
    ماش
    0.43
    獧
    0.43
    POSITIVE LOGITS
     заседа
    0.52
     and
    0.52
     urgently
    0.52
     followed
    0.48
     from
    0.47
     stating
    0.47
     hạng
    0.47
     memorandum
    0.47
     $(".
    0.46
     h
    0.46
    Activations Density 0.000%

    No Known Activations