© 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. 15196
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

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

    The neuron responds to numeric tokens (numbers, dates, measurements, IDs, etc.) in the text.

    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
    يد
    0.90
     Admir
    0.87
    았
    0.82
     Preface
    0.82
     ORNL
    0.81
     ADV
    0.80
     ESL
    0.80
     MHD
    0.78
    ADES
    0.78
     ASE
    0.77
    POSITIVE LOGITS
     впоследствии
    0.75
    వే
    0.74
     guesswork
    0.73
    喑
    0.73
     compromiso
    0.71
     posteriormente
    0.67
    वृद्धि
    0.66
     retomar
    0.66
     умень
    0.66
     realiza
    0.66
    Activations Density 0.000%

    No Known Activations