© 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. 41552
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    all rights reserved

    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
     Debido
    0.46
     Perman
    0.43
     Daarna
    0.43
     Qualquer
    0.43
    あらゆる
    0.43
     Cela
    0.42
     °,
    0.42
     Khi
    0.41
     পড়িয়া
    0.41
     ใด
    0.41
    POSITIVE LOGITS
    ्स
    0.41
     proteinuria
    0.39
    ן
    0.39
     probably
    0.38
    lard
    0.38
     is
    0.37
     candid
    0.37
     was
    0.37
     مدرس
    0.36
    ］
    0.36
    Activations Density 0.002%

    No Known Activations