© 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-16K
    7. 13132
    Prev
    Next
    INDEX
    Explanations

    dates, events, or conditions

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

    the followed by nouns

    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_16k_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
     blijkt
    0.48
    ীনে
    0.41
     многих
    0.40
    数据显示
    0.40
    協
    0.40
    報導
    0.39
    ဏ
    0.39
    িন্ন
    0.39
    隈
    0.38
    ひとつ
    0.38
    POSITIVE LOGITS
    üdis
    0.42
     serán
    0.42
     অথবা
    0.41
     serían
    0.39
     ឬ
    0.39
     Bukan
    0.38
     pourraient
    0.38
    could
    0.38
     अथवा
    0.38
     اقدامات
    0.38
    Activations Density 0.081%

    No Known Activations