© 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. 22-GEMMASCOPE-RES-131K
    7. 32584
    Prev
    Next
    INDEX
    Explanations

    news and media outlets

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

    The neuron selectively activates on numeric tokens—e.g. standalone numbers, years, statistics, and other digit‐based figures.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     havde
    -1.00
    Technik
    -0.93
    RODUCTION
    -0.88
    垆
    -0.87
     hatt
    -0.86
    吭
    -0.83
     威
    -0.82
     Aan
    -0.82
     لهم
    -0.82
     岛
    -0.80
    POSITIVE LOGITS
    bigliamento
    0.90
    ického
    0.89
     first
    0.87
     пър
    0.87
     through
    0.87
    墟
    0.86
    Ótimo
    0.85
    ométrique
    0.85
     prisons
    0.83
    小說
    0.83
    Activations Density 0.004%

    No Known Activations