© 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. 127355
    Prev
    Next
    INDEX
    Explanations

    recognizing specific names and their associations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    絝
    -2.91
    铪
    -2.89
    辔
    -2.73
    豨
    -2.64
     всѣ
    -2.59
    Ꮽ
    -2.58
    anyahu
    -2.55
    ᥆
    -2.52
    ꯹
    -2.52
    できるだけ
    -2.50
    POSITIVE LOGITS
     '
    2.72
    ’
    2.44
    um
    2.31
    й
    2.23
    著名的
    2.17
    [
    2.17
    褔
    2.11
    ?".
    2.09
     staunch
    2.09
    使用
    2.08
    Activations Density 0.005%

    No Known Activations