© 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. 8594
    Prev
    Next
    INDEX
    Explanations

    deployments or initialize

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

    The neuron fires strongly on tokens that contain one or more digits—e.g. multi-digit numbers in monetary amounts or numeric strings in URLs.

    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
     بسر
    0.87
     Sejam
    0.82
     Recordemos
    0.80
     bertanggung
    0.80
     Já
    0.80
     الات
    0.78
     aberrations
    0.78
    ﺩ
    0.78
    াতের
    0.77
    をしている
    0.77
    POSITIVE LOGITS
    ite
    0.88
    {~
    0.84
    ze
    0.82
    engine
    0.79
    
    0.78
    湿
    0.77
    pace
    0.76
    ε
    0.76
    propri
    0.74
    and
    0.73
    Activations Density 0.000%

    No Known Activations