© 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. 76039
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure commands

    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
     pact
    0.43
    பாவ
    0.43
    syllabus
    0.41
    Ტ
    0.41
     सचिवा
    0.40
    norms
    0.40
    Agenda
    0.39
     ostatnich
    0.38
    agenda
    0.38
    scales
    0.38
    POSITIVE LOGITS
     ذلك
    0.43
     called
    0.40
    assing
    0.39
     দামে
    0.38
    auti
    0.38
    iosamente
    0.37
    兗
    0.36
     Huntingdon
    0.36
    偪
    0.36
     జగ
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.