© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130726
    Prev
    Next
    INDEX
    Explanations

    urethra

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

    proper nouns and technical terms appearing in specific text contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -3.17
     unwavering
    -2.98
     unrelenting
    -2.80
    ⢮
    -2.72
     substantial
    -2.67
    л
    -2.67
     unparalleled
    -2.66
     That
    -2.66
    äki
    -2.63
    鋮
    -2.63
    POSITIVE LOGITS
    {
    2.59
    赑
    2.56
    le
    2.47
     a
    2.44
    鉿
    2.42
    咴
    2.41
     The
    2.39
    苤
    2.36
    咵
    2.36
    ?
    2.31
    Activations Density 0.094%

    No Known Activations