© 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. 6824
    Prev
    Next
    INDEX
    Explanations

    sequential numbers and punctuation

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

    The neuron is highly activated by numeric tokens, i.e. standalone numbers.

    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
     paralysie
    0.70
     diámetro
    0.68
    🍯
    0.68
     Tuttavia
    0.66
    কিন্তু
    0.64
    ❄
    0.64
     แต
    0.63
    ƙ
    0.63
    kadang
    0.63
    ifford
    0.63
    POSITIVE LOGITS
     equipment
    0.77
     marker
    0.71
    equipment
    0.66
    ায়ন
    0.65
     armament
    0.64
     manufacturer
    0.63
     undertaking
    0.62
     successor
    0.61
     print
    0.61
     answer
    0.61
    Activations Density 0.001%

    No Known Activations