© 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. 63620
    Prev
    Next
    INDEX
    Explanations

    discuss languages photo numbers Acquisitions

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

    laws require payment mandates

    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
    哨
    0.48
    է
    0.48
     অথবা
    0.46
     ذاتی
    0.44
     cidade
    0.43
     நோக்கி
    0.43
    riente
    0.43
     או
    0.43
     челу
    0.43
    cte
    0.43
    POSITIVE LOGITS
    ند
    0.45
     Lips
    0.44
     Abhäng
    0.44
    組合
    0.43
     Hits
    0.43
     Fär
    0.43
    年
    0.43
     Combin
    0.43
     Acquisitions
    0.42
     fär
    0.41
    Activations Density 0.000%

    No Known Activations