© 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. 95828
    Prev
    Next
    INDEX
    Explanations

    HARTFORD drive thru Artist Pension ISO/

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

    This neuron picks out numeric tokens (numbers) 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
     even
    -1.62
     with
    -1.60
     has
    -1.60
     one
    -1.59
     only
    -1.57
     before
    -1.57
     first
    -1.46
     should
    -1.46
     cleverly
    -1.41
     at
    -1.37
    POSITIVE LOGITS
     nimmer
    1.43
    皤
    1.41
    Yeni
    1.41
    andering
    1.40
     schuldig
    1.38
     Heilige
    1.35
     randonnée
    1.33
    Zna
    1.32
    鱨
    1.30
     cinq
    1.27
    Activations Density 0.000%

    No Known Activations