© 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. 57345
    Prev
    Next
    INDEX
    Explanations

    out of domain, margin, mid

    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
    お
    0.53
    標
    0.50
    <h3>
    0.46
    Seasonal
    0.46
     dataSource
    0.46
     Над
    0.45
    $(
    0.44
     secondes
    0.43
    連
    0.43
    <h2>
    0.43
    POSITIVE LOGITS
    akova
    0.48
     Yucatan
    0.47
    akannya
    0.46
    retrieve
    0.43
     Europeans
    0.43
    лната
    0.43
     भटक
    0.42
    sset
    0.42
    rt
    0.42
     Ecommerce
    0.41
    Activations Density 0.003%

    No Known Activations