© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114185
    Prev
    Next
    INDEX
    Explanations

    google followed by . or word

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

    references to Google in technical/programming contexts, particularly in code, API documentation, and technology news.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
    '
    -1.91
     Você
    -1.91
    比如说
    -1.85
     They
    -1.77
    珵
    -1.71
    比如
    -1.69
    </b>
    -1.68
     anche
    -1.68
     is
    -1.66
    訁
    -1.63
    POSITIVE LOGITS
    0
    2.27
    のは
    1.74
     в
    1.73
     of
    1.69
     methode
    1.65
    気がする
    1.65
     метода
    1.65
    蟊
    1.63
    }
    1.63
    ୈ
    1.62
    Activations Density 0.054%

    No Known Activations