© 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. 170656
    Prev
    Next
    INDEX
    Explanations

    business employers and customers

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

    legal and financial estimations

    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
     extends
    0.50
     köt
    0.50
     मंजूरी
    0.48
     ジャケット
    0.47
     formalities
    0.47
     a
    0.45
     at
    0.45
    íz
    0.43
     denies
    0.43
     formally
    0.42
    POSITIVE LOGITS
     দেখিয়া
    0.44
    astico
    0.43
    عند
    0.42
    ايبي
    0.41
    اب
    0.40
    BIUM
    0.39
    貔
    0.39
     Subscribers
    0.38
    บุรี
    0.38
    畊
    0.38
    Activations Density 0.003%

    No Known Activations