© 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. 37690
    Prev
    Next
    INDEX
    Explanations

    tail and trail

    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
    ни
    0.73
    лер
    0.62
    ле
    0.61
    си
    0.61
    ну
    0.55
    ?
    0.54
     ограниче
    0.54
    τε
    0.53
     llave
    0.53
    メイク
    0.52
    POSITIVE LOGITS
     tail
    0.88
    Tail
    0.86
     Tails
    0.75
     Tail
    0.74
     tails
    0.71
    Trailing
    0.70
    尾
    0.70
     trailing
    0.69
    Trail
    0.62
    Trails
    0.62
    Activations Density 0.025%

    No Known Activations