© 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. 504
    Prev
    Next
    INDEX
    Explanations

    not directly visible

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

    This neuron selectively activates on content nouns referring to general concepts or topics (e.g. “pattern,” “instruction,” “battles,” “wisdom”).

    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
     以及
    0.49
     ۽
    0.46
     និង
    0.45
     både
    0.45
     そして
    0.43
     včetně
    0.43
     sowohl
    0.43
     و
    0.41
    そして
    0.41
     sekä
    0.40
    POSITIVE LOGITS
     sondern
    0.85
    而是
    0.84
     nor
    0.75
     никаких
    0.68
     żad
    0.66
     whatsoever
    0.66
     anymore
    0.64
     ningún
    0.64
     hanem
    0.64
     herhangi
    0.64
    Activations Density 0.000%

    No Known Activations