© 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. 101431
    Prev
    Next
    INDEX
    Explanations

    Heated Private, United States, SiO₂

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

    single

    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
     f
    0.56
     רי
    0.53
     הת
    0.49
     ถ
    0.48
     పు
    0.47
     Dup
    0.47
     添加
    0.46
     finals
    0.46
     ف
    0.45
     ጥሩ
    0.45
    POSITIVE LOGITS
    isce
    0.57
    ت
    0.55
    ээр
    0.54
    ن
    0.52
    gk
    0.50
    મારા
    0.50
    تور
    0.49
    elevation
    0.49
    ले
    0.48
    rivers
    0.47
    Activations Density 0.003%

    No Known Activations