© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9488
    Prev
    Next
    INDEX
    Explanations

    programming or technical context

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

    The neuron spotlights occurrences of the token “Noc” (as in the author name “Nocedal”) in academic citation entries.

    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_31_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
     injecting
    0.63
     reprogramming
    0.62
     binding
    0.58
     compromiso
    0.58
     reprogram
    0.57
     compromet
    0.57
    氮
    0.54
     transduction
    0.54
     allergen
    0.54
     inject
    0.52
    POSITIVE LOGITS
     by
    0.60
    <0xA7>
    0.55
    蘋
    0.55
     oleh
    0.54
     тво
    0.54
    ysta
    0.54
    껭
    0.54
    ঙ্গিক
    0.52
     oor
    0.51
    OPA
    0.51
    Activations Density 0.000%

    No Known Activations