© 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. 14066
    Prev
    Next
    INDEX
    Explanations

    keywords and tags

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

    keywords

    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
    笑道
    0.45
     Tonight
    0.45
     honoured
    0.42
    ్లా
    0.41
     Land
    0.41
     सदस्यीय
    0.40
    🏿
    0.40
    门口
    0.39
    uradaki
    0.39
    쬐
    0.39
    POSITIVE LOGITS
     keywords
    0.92
    Keywords
    0.76
     keyword
    0.71
     Keywords
    0.71
    keywords
    0.68
    关键词
    0.61
    keyword
    0.59
    キーワード
    0.55
    KEYWORDS
    0.55
    Keyword
    0.52
    Activations Density 0.030%

    No Known Activations