© 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. 248608
    Prev
    Next
    INDEX
    Explanations

    for extras

    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
    চট্টগ্রাম
    0.50
    +}$
    0.48
    শাহ
    0.48
    లన
    0.47
    Tommy
    0.47
     सूर्यकुमार
    0.46
    лых
    0.44
    श्रे
    0.43
    ప్ప
    0.42
    ಖ
    0.42
    POSITIVE LOGITS
     kt
    0.50
     箱
    0.49
     ir
    0.49
     ft
    0.49
     pie
    0.47
    ansk
    0.46
     ആണ്
    0.46
     maan
    0.46
    galo
    0.46
     odgov
    0.46
    Activations Density 0.001%

    No Known Activations