© 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. 9270
    Prev
    Next
    INDEX
    Explanations

    UI layout code

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

    The neuron fires on numeric expressions and measurements (e.g. digit sequences, quantities, and dimensions).

    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
    visible
    0.63
    ptor
    0.61
    mole
    0.59
    balls
    0.59
    inicio
    0.59
    воро
    0.59
     молеку
    0.58
    弈
    0.58
     கூடாது
    0.58
    linux
    0.57
    POSITIVE LOGITS
     나눠
    0.73
     TRS
    0.73
    اؤ
    0.69
     เหล
    0.65
     Propaganda
    0.64
     アン
    0.64
     theres
    0.64
     ISS
    0.63
    ומים
    0.63
     मुद्दों
    0.62
    Activations Density 0.002%

    No Known Activations