© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14914
    Prev
    Next
    INDEX
    Explanations

    financial, impossible, neighborhood, 1

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

    The neuron activates on words appearing directly before numbers or other quantitative expressions (e.g. those immediately preceding dates, statistics, percentages, measurements, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ς
    0.95
    می
    0.89
     appla
    0.86
    ьогодні
    0.79
    ्स
    0.79
    mnopqrst
    0.79
     вдруг
    0.78
    ﻡ
    0.77
    得意
    0.75
     усі
    0.73
    POSITIVE LOGITS
     spez
    0.74
    fowl
    0.73
     glab
    0.71
    ."),
    0.70
    樁
    0.70
    ibel
    0.69
    iable
    0.67
     निव
    0.67
     conviene
    0.66
    ikle
    0.64
    Activations Density 0.000%

    No Known Activations