© 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. 147510
    Prev
    Next
    INDEX
    Explanations

    valued available facility three

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

    specific keywords and modifiers

    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
    用
    0.47
    Stamp
    0.46
    鹑
    0.45
     Gifts
    0.44
    Gift
    0.44
    めちゃ
    0.43
     Bb
    0.43
     pakas
    0.43
    炡
    0.43
    ⟥
    0.42
    POSITIVE LOGITS
     fémin
    0.51
    atien
    0.50
     extracting
    0.48
     elaborate
    0.47
     restructuring
    0.46
     crystallization
    0.46
     écran
    0.46
     quelles
    0.46
     quantification
    0.45
    à
    0.45
    Activations Density 0.000%

    No Known Activations