© 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. 57105
    Prev
    Next
    INDEX
    Explanations

    dravet syndrome

    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
    残酷
    0.47
     दख
    0.47
    Боль
    0.46
    ⴼ
    0.45
    ྥ
    0.45
    ᱞ
    0.45
    ელ
    0.44
    媧
    0.43
    ів
    0.43
    ავ
    0.42
    POSITIVE LOGITS
    时间内
    0.54
     dirigente
    0.47
     Series
    0.46
     totales
    0.45
     streamlines
    0.44
     Ejecutivo
    0.44
    ;,
    0.43
    ),
    0.43
    。。。
    0.43
     次元
    0.42
    Activations Density 0.009%

    No Known Activations