© 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-262K
    7. 29725
    Prev
    Next
    INDEX
    Explanations

    seizure during a speech

    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_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
    Gaussian
    0.46
    citizens
    0.45
    Recall
    0.44
    $),
    0.44
    Recognition
    0.43
    ()],
    0.43
    อื่น
    0.42
    RE
    0.42
    OPT
    0.42
    recall
    0.42
    POSITIVE LOGITS
    僄
    0.54
     từ
    0.50
    íř
    0.49
    旕
    0.47
    從
    0.46
    㦣
    0.46
     Profesor
    0.45
    壃
    0.45
    挕
    0.45
    腖
    0.45
    Activations Density 0.003%

    No Known Activations