© 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. 9596
    Prev
    Next
    INDEX
    Explanations

    latex

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

    The neuron fires strongly on the very first content token of a new segment or section (i.e. it marks the beginning of each text block).

    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
     stř
    0.87
     Nej
    0.84
    꿔
    0.77
     전자
    0.77
     EU
    0.73
     tenths
    0.73
     qRT
    0.73
    rú
    0.73
     власти
    0.73
     particulares
    0.72
    POSITIVE LOGITS
    儕
    0.82
    '
    0.78
    ctuation
    0.78
    hepatic
    0.77
    啈
    0.74
    correlated
    0.73
    ंसद
    0.72
    ampled
    0.71
    壺
    0.71
    intelligent
    0.71
    Activations Density 0.000%

    No Known Activations