© 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. 15137
    Prev
    Next
    INDEX
    Explanations

    action item or status

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

    The neuron fires on the very first real word of a new segment or sentence, effectively marking segment- or sentence-initial tokens.

    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
    in
    0.98
    to
    0.92
    č
    0.86
    t
    0.80
    ew
    0.79
    tf
    0.79
    em
    0.78
    ва
    0.78
    tw
    0.77
    ff
    0.76
    POSITIVE LOGITS
     exfol
    1.06
     pout
    0.98
     réduit
    0.98
     ritor
    0.97
     ratione
    0.93
     chuột
    0.93
     delici
    0.91
     ligero
    0.91
     cappuccino
    0.91
     Encore
    0.89
    Activations Density 0.001%

    No Known Activations