© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49414
    Prev
    Next
    INDEX
    Explanations

    finding plugin attachments

    np_acts-logits-general · gemini-2.5-flash-lite

    dust motes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gak
    0.52
     Très
    0.49
    ès
    0.48
     メール
    0.46
    ings
    0.46
    鋼
    0.46
     caffè
    0.46
    вая
    0.46
    浴
    0.46
    ‌ها
    0.46
    POSITIVE LOGITS
    determining
    0.55
    n
    0.47
    tive
    0.45
    key
    0.45
    sunrise
    0.45
    dependency
    0.45
    a
    0.45
     जिम्मे
    0.45
    sust
    0.44
    demand
    0.43
    Activations Density 0.000%

    No Known Activations