© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74375
    Prev
    Next
    INDEX
    Explanations

    CODE SNIPPETS AND HEADERS

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

    This neuron detects tab characters (literal “\t” escapes or indentation tabs) in the text.

    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
     We
    -1.71
     
    -1.67
     I
    -1.67
     with
    -1.57
     The
    -1.53
    ;
    -1.50
     those
    -1.47
     other
    -1.41
     mudanças
    -1.37
     různých
    -1.35
    POSITIVE LOGITS
    %;">
    1.69
     tille
    1.68
     CRIST
    1.65
    wwwwwwww
    1.64
    👎
    1.63
     FEBR
    1.62
    😂😂😂
    1.60
    ❤❤
    1.59
    uteurs
    1.58
     ENGL
    1.52
    Activations Density 0.031%

    No Known Activations