© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51926
    Prev
    Next
    INDEX
    Explanations

    inflammation definitions

    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
    пи
    0.47
    什么
    0.45
    తా
    0.44
    δη
    0.44
    เพื่อ
    0.43
    LE
    0.43
    荑
    0.43
    दम
    0.43
    מה
    0.43
     цент
    0.42
    POSITIVE LOGITS
     verschied
    0.45
    '.
    0.44
    .{
    0.44
    slideDuplicate
    0.44
     fruitful
    0.43
     Wię
    0.42
     المختلفة
    0.42
     agreeing
    0.42
     conferred
    0.42
    㐱
    0.42
    Activations Density 0.014%

    No Known Activations