© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14686
    Prev
    Next
    INDEX
    Explanations

    float literals followed by punctuation

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

    The neuron is highly activated by numeric literal tokens—especially floating-point numbers (digits, decimal points, and the “f” suffix).

    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
     their
    -2.09
     a
    -1.95
     this
    -1.63
     of
    -1.49
     which
    -1.48
     where
    -1.45
     (
    -1.38
     solely
    -1.35
     either
    -1.35
     providing
    -1.34
    POSITIVE LOGITS
     поддержка
    1.99
    
    1.91
    mathrm
    1.90
     некоторых
    1.85
     insane
    1.78
     estrictamente
    1.77
     VERY
    1.74
     quando
    1.73
     reemplazar
    1.70
     llenar
    1.66
    Activations Density 0.005%

    No Known Activations