© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11900
    Prev
    Next
    INDEX
    Explanations

    video length and title

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

    The neuron specifically fires on numeric tokens that include decimal points.

    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
    د
    0.95
    da
    0.87
    society
    0.82
    daq
    0.77
    singular
    0.76
    saw
    0.75
    sens
    0.74
    secondary
    0.72
    s
    0.72
    par
    0.70
    POSITIVE LOGITS
     pretzels
    0.77
     Macs
    0.75
     overalls
    0.75
     sweatshirts
    0.73
     wasps
    0.71
    ές
    0.71
     scanf
    0.70
     twin
    0.69
     থানার
    0.69
     stof
    0.69
    Activations Density 0.002%

    No Known Activations