© 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. 83681
    Prev
    Next
    INDEX
    Explanations

    current blog

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

    This neuron detects floating‐point numeric literals (decimal numbers) in code or markup.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     contesta
    -1.53
     cristian
    -1.47
     lanterna
    -1.45
    _'+
    -1.45
     censura
    -1.43
    ↵
    -1.41
     can
    -1.40
     tortura
    -1.39
    >
    -1.38
     it
    -1.38
    POSITIVE LOGITS
     from
    1.45
    靱
    1.44
    četně
    1.38
     già
    1.38
    таки
    1.36
     sebagainya
    1.35
     dát
    1.33
    たっぷり
    1.33
    ícias
    1.31
    ujemy
    1.30
    Activations Density 0.004%

    No Known Activations