© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40904
    Prev
    Next
    INDEX
    Explanations

    complex topics and debates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecto
    0.43
    茄
    0.42
    ที่
    0.42
    yuk
    0.42
    견
    0.41
    หย
    0.40
    yta
    0.40
     تبدیلی
    0.40
     clim
    0.40
    暑
    0.40
    POSITIVE LOGITS
     sólo
    0.46
     nesse
    0.46
     DOS
    0.43
     svjets
    0.42
     SEPT
    0.41
     nello
    0.40
     mancanza
    0.40
     bunların
    0.39
     qualcuno
    0.38
     ওসমান
    0.38
    Activations Density 0.002%

    No Known Activations