© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23792
    Prev
    Next
    INDEX
    Explanations

    epilepsy and seizures

    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_40_width_262k_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
    imbus
    0.39
    າມາດ
    0.39
    任务
    0.37
     superpowers
    0.37
     athletic
    0.36
    皑
    0.36
     protect
    0.36
     powered
    0.36
    毫
    0.36
    ainte
    0.35
    POSITIVE LOGITS
     epile
    0.58
     seizure
    0.56
     seizures
    0.55
     epilepsy
    0.51
     epilept
    0.51
     Epilepsy
    0.50
     Epile
    0.48
     epileptic
    0.45
     Migration
    0.43
     Drav
    0.43
    Activations Density 0.005%

    No Known Activations