© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 223687
    Prev
    Next
    INDEX
    Explanations

    posted and displayed

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

    assist, exception, AI, macro, script

    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
    藺
    0.54
    リース
    0.49
    alea
    0.48
    ರ್ಮ
    0.47
    びに
    0.46
     carico
    0.46
     stein
    0.46
    opes
    0.46
    ﻛ
    0.46
    ومی
    0.45
    POSITIVE LOGITS
     режими
    0.49
     पात्र
    0.47
     البروت
    0.47
     yılı
    0.46
    क्लेव
    0.46
     trứng
    0.46
     Nası
    0.46
     обсу
    0.46
     તેમણે
    0.45
    был
    0.45
    Activations Density 0.001%

    No Known Activations