© 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. 73594
    Prev
    Next
    INDEX
    Explanations

    proper noun sequences and punctuation

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

    The main thing this neuron does is detect numeric tokens (numbers and numeric expressions) 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_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
     their
    -2.52
     more
    -2.25
     at
    -2.23
     both
    -2.20
     not
    -2.17
     or
    -2.13
     all
    -1.99
     first
    -1.92
     less
    -1.91
     on
    -1.86
    POSITIVE LOGITS
     intrigu
    1.79
     compe
    1.76
     Dinas
    1.70
     REALLY
    1.70
     AMAZING
    1.67
    などが
    1.67
     カジュアル
    1.65
     quintessential
    1.63
     diagno
    1.63
     blossoming
    1.62
    Activations Density 0.016%

    No Known Activations