© 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. 15407
    Prev
    Next
    INDEX
    Explanations

    COUNT, SUM, AVERAGE, MIN, MAX

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

    The neuron is triggered by numeric measurements or figures, especially decimal‐formatted 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
    י
    0.97
     (
    0.79
     sicher
    0.78
     অন্যান্য
    0.73
     regras
    0.73
     stow
    0.71
     studied
    0.71
     sampled
    0.71
    その他の
    0.71
    ي
    0.71
    POSITIVE LOGITS
     впечатление
    0.94
    o
    0.93
     morphism
    0.86
    رسٹ
    0.84
    t
    0.81
    वियस
    0.80
    MOR
    0.79
    尔
    0.78
    uine
    0.77
     คน
    0.76
    Activations Density 0.002%

    No Known Activations