© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124097
    Prev
    Next
    INDEX
    Explanations

    capital market, blood, picture, historical section

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

    terms related to specific technical or institutional locations like capital markets, hospitals, MTR stations, and technical terminology.

    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
     to
    -2.69
     if
    -2.56
     it
    -2.31
     not
    -2.14
     in
    -2.08
     because
    -1.98
     which
    -1.97
     for
    -1.95
     when
    -1.94
     this
    -1.76
    POSITIVE LOGITS
    );*/
    1.63
    呓
    1.61
    voyez
    1.59
     faciliter
    1.57
    issez
    1.57
    ']=
    1.55
    ']),
    1.54
     anpass
    1.52
     bicicleta
    1.50
     mètre
    1.50
    Activations Density 0.377%

    No Known Activations