© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9530
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical documents

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

    The neuron strongly activates on words that immediately precede or introduce numeric expressions (i.e. tokens directly followed by 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
     alcoved
    0.81
    拌
    0.81
    第一个
    0.80
    让自己
    0.80
     দৃ
    0.78
     sœur
    0.75
    Inicial
    0.75
    여행
    0.75
    argaan
    0.75
    Bonnie
    0.75
    POSITIVE LOGITS
    あとは
    0.66
    ᄉ
    0.65
    ↵
    0.64
     (…)
    0.64
     disseminated
    0.64
    あと
    0.63
     Evangel
    0.63
     SARS
    0.63
    ᄊ
    0.62
    дии
    0.61
    Activations Density 0.000%

    No Known Activations