© 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. 49973
    Prev
    Next
    INDEX
    Explanations

    Davidson motorcycle, after short, term demoral, successful track

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

    vendor approval and contact

    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
     Scandinavia
    0.48
     Scandin
    0.47
    扆
    0.46
     स्किल
    0.46
    的产品
    0.45
     multiverse
    0.44
     ज़िंदगी
    0.44
     lím
    0.44
     डिजा
    0.43
     انگل
    0.43
    POSITIVE LOGITS
     inserting
    0.48
    插入
    0.45
    挿
    0.43
     criminal
    0.42
     activating
    0.41
     Inserting
    0.41
    ্ব
    0.41
     insertion
    0.40
    দ
    0.40
    緞
    0.40
    Activations Density 0.000%

    No Known Activations