© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16325
    Prev
    Next
    INDEX
    Explanations

    create, plan, trigger, bundle, passive

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

    The neuron activates on numerical tokens (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
    8
    0.91
    uo
    0.88
    0
    0.87
    od
    0.81
    9
    0.81
    6
    0.75
    бні
    0.71
    ạm
    0.71
    1
    0.69
    <0xE1>
    0.68
    POSITIVE LOGITS
     койма
    0.84
     اچھا
    0.81
     اگلے
    0.81
     दरम्यान
    0.80
    nieuw
    0.80
     доку
    0.79
    ड्रो
    0.77
    ტის
    0.74
     ق
    0.74
    backer
    0.74
    Activations Density 0.000%

    No Known Activations