© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2624
    Prev
    Next
    INDEX
    Explanations

    numbers like 8

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

    The neuron is specialized in spotting numeric tokens (multi­digit numbers and numerical expressions) 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_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
    鴦
    0.81
     bych
    0.78
     Gardens
    0.77
     bpm
    0.77
    合う
    0.74
     hashing
    0.73
     Claud
    0.73
     bandwagon
    0.72
     pounds
    0.71
     waving
    0.71
    POSITIVE LOGITS
    氇
    1.05
    ieth
    0.97
    een
    0.92
    Bit
    0.91
    BIT
    0.80
    интере
    0.73
    pré
    0.70
    <0x80>
    0.70
    puesta
    0.70
    nå
    0.69
    Activations Density 0.319%

    No Known Activations