© 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. 90842
    Prev
    Next
    INDEX
    Explanations

    outcomes, issuing receipts

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

    focus on, look for, evoke sympathy

    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
    кистон
    0.48
     hyperlinks
    0.46
     salud
    0.45
    라이언트
    0.45
    법
    0.45
    коном
    0.44
     மருந்த
    0.44
    ตอน
    0.44
    法
    0.44
    当时的
    0.43
    POSITIVE LOGITS
    spo
    0.47
    5
    0.46
    4
    0.46
     Life
    0.44
    life
    0.44
    6
    0.43
    ue
    0.43
    X
    0.43
    8
    0.43
    og
    0.42
    Activations Density 0.005%

    No Known Activations