© 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. 71719
    Prev
    Next
    INDEX
    Explanations

    contribution to classes

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

    qualified comparisons

    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
    ges
    0.42
     transaksi
    0.42
     Bukan
    0.41
    媤
    0.41
     và
    0.41
    van
    0.40
    🔎
    0.40
    ুজ
    0.40
     Riviera
    0.39
    ম্‌
    0.39
    POSITIVE LOGITS
    之力
    0.48
    fcntl
    0.39
     supplemented
    0.38
     phil
    0.38
    اسی
    0.38
     déficit
    0.37
    accueil
    0.37
     güç
    0.36
    تل
    0.36
     perte
    0.36
    Activations Density 0.000%

    No Known Activations