© 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. 64539
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    This neuron fires on numeric tokens (sequences of digits, often with attached units), i.e. it detects numbers in the text.

    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
     bezw
    -0.82
    PlayerPrefs
    -0.82
    加
    -0.77
    怔
    -0.77
     любого
    -0.76
    は
    -0.75
    pios
    -0.74
     Eier
    -0.73
    stück
    -0.73
    prove
    -0.73
    POSITIVE LOGITS
     tilbage
    0.90
    Затем
    0.88
    Ссылка
    0.88
    萘
    0.84
    Срок
    0.83
     carga
    0.82
    Коммента
    0.81
    только
    0.81
     before
    0.80
    можно
    0.80
    Activations Density 0.041%

    No Known Activations