© 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. 190862
    Prev
    Next
    INDEX
    Explanations

    first partsNo documentsEverything besidespiece where

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

    informational phrases

    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
    y
    0.65
    icycle
    0.49
    o
    0.48
    atonic
    0.48
    at
    0.47
    al
    0.47
    kere
    0.46
    mobile
    0.46
    olino
    0.46
    gow
    0.46
    POSITIVE LOGITS
    د
    0.55
     породы
    0.54
    อน
    0.50
    д
    0.50
     конечно
    0.49
     বস্তু
    0.49
    則是
    0.48
    كذا
    0.48
    ForEach
    0.47
     Сы
    0.47
    Activations Density 0.003%

    No Known Activations