© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15380
    Prev
    Next
    INDEX
    Explanations

    periods and sites

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

    not or not followed by distinguishing words

    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
     lái
    0.54
    Mg
    0.52
     mał
    0.48
     మార్
    0.46
     Франции
    0.44
     दहेज
    0.44
    )>\
    0.43
     ಸ್ಥಳ
    0.43
     फॉरेस्ट
    0.42
    çük
    0.42
    POSITIVE LOGITS
    ي
    0.61
    development
    0.53
    د
    0.49
    أ
    0.49
    research
    0.47
    live
    0.47
    و
    0.46
     overlooks
    0.46
    opt
    0.45
     axioms
    0.45
    Activations Density 0.002%

    No Known Activations