© 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. 72050
    Prev
    Next
    INDEX
    Explanations

    modifiers

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

    average daily

    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
    зами
    0.38
     سو
    0.37
     비슷한
    0.36
     پری
    0.36
     cả
    0.35
     بہت
    0.34
    ^*\
    0.34
     ون
    0.34
     በአ
    0.33
     veoma
    0.33
    POSITIVE LOGITS
    इंडिया
    0.38
    ЕН
    0.38
    ंदीदा
    0.38
    स्टेबल
    0.38
    রুদ্ধ
    0.37
     mettent
    0.36
    ግራ
    0.35
    ಟ್ರ
    0.34
     gridSize
    0.34
     proporcionan
    0.34
    Activations Density 0.158%

    No Known Activations