© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    black and white

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

    the neuron consistently activates on numeric tokens (i.e. digits or numbers) 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
    (
    0.72
    не
    0.70
    )
    0.69
    ي
    0.66
    وب
    0.66
    ে
    0.66
    يي
    0.65
    ONIUM
    0.65
    {
    0.65
    Enh
    0.65
    POSITIVE LOGITS
     diariamente
    0.85
     sådan
    0.85
     Padres
    0.85
     át
    0.83
    슨
    0.83
     EVs
    0.82
     pidió
    0.82
     diálogo
    0.81
     salariés
    0.81
     están
    0.80
    Activations Density 0.000%

    No Known Activations