© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11608
    Prev
    Next
    INDEX
    Explanations

    value treatments; dependence statements

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

    The neuron activates on numeric tokens (i.e. any token made up of digits).

    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_31_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
    Puerto
    0.63
    ೧
    0.59
    Zie
    0.58
    Bienvenidos
    0.55
    Shows
    0.55
    這一
    0.54
    മായിരുന്നു
    0.53
    ೬
    0.53
    Cors
    0.52
    PayPal
    0.52
    POSITIVE LOGITS
     carbonyl
    0.61
     incumbent
    0.59
     sparsebundle
    0.54
     aggregator
    0.54
     pakai
    0.54
     ಜಿಲ್ಲ
    0.52
     जिल्ह्यातील
    0.52
     mechanisms
    0.52
     dependence
    0.51
     derivative
    0.51
    Activations Density 0.000%

    No Known Activations