© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11464
    Prev
    Next
    INDEX
    Explanations

    data processing units

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

    The neuron fires on code identifiers on the left‐hand side of assignments when they’re being set to numeric constants.

    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
    čkog
    0.64
     Sánchez
    0.56
    urum
    0.54
    ־
    0.54
    _
    0.53
     हारे
    0.52
    ovskii
    0.52
    ojen
    0.52
     Allocate
    0.52
    ό
    0.51
    POSITIVE LOGITS
     जाता
    0.56
     Patri
    0.56
    तात
    0.55
     جاتا
    0.55
    гістра
    0.53
     tif
    0.52
     bunting
    0.51
    traditional
    0.50
     جاتی
    0.50
     gry
    0.50
    Activations Density 0.000%

    No Known Activations