© 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. 9762
    Prev
    Next
    INDEX
    Explanations

    programming code and lists

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

    The neuron fires on isolated short tokens—things like standalone numbers, abbreviations, unit symbols, or URL fragments.

    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
     principales
    0.80
    VIA
    0.78
     arrondi
    0.77
     系列
    0.75
    }`));
    0.75
     idxf
    0.75
     elucidated
    0.74
    Accuracy
    0.74
    Argument
    0.73
     arrondies
    0.71
    POSITIVE LOGITS
    سة
    0.82
     doping
    0.78
     Rhine
    0.77
    ’
    0.77
    rinth
    0.74
     spree
    0.74
     savor
    0.73
     legislature
    0.73
     lantern
    0.72
     Karaoke
    0.72
    Activations Density 0.002%

    No Known Activations