© 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. 48324
    Prev
    Next
    INDEX
    Explanations

    start of section or document

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

    The neuron strongly activates on backslash characters (often used in code or markup escapes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ();
    -2.03
    );
    -2.03
    ">
    -1.95
     will
    -1.87
    k
    -1.81
    ed
    -1.77
     by
    -1.74
    I
    -1.70
    b
    -1.63
    を
    -1.63
    POSITIVE LOGITS
    杙
    1.80
     resultCode
    1.66
     fiscale
    1.50
    罒
    1.47
     seuls
    1.45
    penser
    1.43
     которы
    1.42
     pageNo
    1.41
     goûts
    1.40
    誂
    1.40
    Activations Density 0.000%

    No Known Activations