© 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. 36503
    Prev
    Next
    INDEX
    Explanations

    my neighbor

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

    lists, orders, and context

    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
     watersheds
    0.42
    డ్‌
    0.41
    浜
    0.41
    𝙧
    0.40
    nes
    0.40
    時候
    0.40
     গুণ
    0.39
     florals
    0.39
    ﻔ
    0.39
    🤖
    0.39
    POSITIVE LOGITS
    Contin
    0.49
     prend
    0.48
     atteggi
    0.46
     پرون
    0.46
    Approx
    0.45
     Vivekan
    0.45
     पोजीशन
    0.45
     berfungsi
    0.43
     facie
    0.43
    asiti
    0.43
    Activations Density 0.000%

    No Known Activations