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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28234
    Prev
    Next
    INDEX
    Explanations

    physics and computation

    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
    touch
    0.45
    ль
    0.44
    다
    0.43
    теря
    0.43
    monthly
    0.42
    ים
    0.42
    impl
    0.41
    can
    0.41
    computer
    0.41
    у
    0.41
    POSITIVE LOGITS
     Nxf
    0.44
     cognizant
    0.44
     pathophysiology
    0.43
     konfer
    0.43
     capaces
    0.42
     œuvre
    0.42
     TODO
    0.42
     Phy
    0.42
     delineated
    0.41
     KDE
    0.41
    Activations Density 0.006%

    No Known Activations