© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    time units and quantities

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

    This neuron fires on the very first content word that begins a new segment or sentence.

    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
     Horus
    0.86
     Changer
    0.86
     Goku
    0.83
     nCount
    0.82
     ARRAY
    0.80
     Gaia
    0.80
     Indra
    0.80
    ﺭ
    0.80
     STRU
    0.79
     GOD
    0.78
    POSITIVE LOGITS
    ducted
    0.79
    টুকু
    0.71
    ities
    0.71
    orter
    0.70
    ization
    0.70
    ained
    0.70
    usi
    0.70
    孀
    0.68
    formatted
    0.68
    trimmed
    0.68
    Activations Density 0.000%

    No Known Activations