© 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. 10-GEMMASCOPE-RES-131K
    7. 42329
    Prev
    Next
    INDEX
    Explanations

    numeric types in code

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

    The neuron fires on numeric literal tokens (numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    either
    -2.16
     précieux
    -2.00
     retten
    -1.91
     brosse
    -1.91
     hemen
    -1.83
    ik
    -1.79
    gave
    -1.78
     Entdecken
    -1.77
    在我
    -1.76
    秾
    -1.74
    POSITIVE LOGITS
     and
    2.97
    </h3>
    2.02
    fucker
    1.81
     because
    1.77
     with
    1.68
    💞
    1.61
     during
    1.59
     voorbere
    1.57
    🥂
    1.56
    💗
    1.55
    Activations Density 0.006%

    No Known Activations