© 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. 22-GEMMASCOPE-RES-131K
    7. 95795
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron detects standalone numeric tokens (e.g. years, volume/issue/page numbers, and other numbers).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -1.10
     those
    -1.05
     another
    -0.98
     what
    -0.96
     LINK
    -0.94
     some
    -0.92
     their
    -0.90
    ěř
    -0.90
     this
    -0.88
    質な
    -0.88
    POSITIVE LOGITS
    着脸
    1.03
    ほとん
    0.98
    が
    0.95
     منهم
    0.95
    গু
    0.93
     Họ
    0.91
    óta
    0.91
    schuhe
    0.90
    での
    0.88
     имеет
    0.88
    Activations Density 0.003%

    No Known Activations