© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    keyword-value pairs or technical descriptions

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

    the neuron activates on numeric tokens—especially multi‐digit numbers and decimals used as identifiers or references.

    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
    le
    0.82
    ón
    0.79
    (),
    0.78
    児童
    0.76
    ken
    0.75
    ()):
    0.74
    くれました
    0.71
    λ
    0.71
    untungan
    0.70
    joe
    0.69
    POSITIVE LOGITS
     risks
    0.94
     chemicals
    0.91
     calls
    0.90
     rules
    0.88
     debuts
    0.87
     drives
    0.86
     debates
    0.86
     gifts
    0.86
     conducts
    0.85
     treasures
    0.85
    Activations Density 0.005%

    No Known Activations