© 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. 211882
    Prev
    Next
    INDEX
    Explanations

    produced by

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

    Organization, efficiency, and policy

    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
     冷
    0.54
     subtypes
    0.50
     classifying
    0.49
     desenvolver
    0.48
     experimented
    0.46
     স্বাক্ষর
    0.46
     ventana
    0.45
     corrida
    0.45
    ⓷
    0.45
     develop
    0.45
    POSITIVE LOGITS
    e
    0.62
    a
    0.60
    Organization
    0.55
    Incoming
    0.54
    Education
    0.53
    et
    0.51
    Online
    0.51
    Presentation
    0.50
    Holiday
    0.50
    Util
    0.50
    Activations Density 0.000%

    No Known Activations