© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43778
    Prev
    Next
    INDEX
    Explanations

    address, side, NC, Migration, alternating, up

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

    physical forms or structures

    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
     scrape
    0.49
     「
    0.47
     wonderful
    0.46
     scraped
    0.46
    不足
    0.46
    スキー
    0.46
     gist
    0.46
     scraping
    0.45
     skier
    0.45
     Oekra
    0.44
    POSITIVE LOGITS
    al
    0.61
    iu
    0.55
    alers
    0.51
    eme
    0.49
    л
    0.49
     नेक्स्ट
    0.49
    rene
    0.48
    aların
    0.47
    ua
    0.46
    álogo
    0.46
    Activations Density 0.000%

    No Known Activations