© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 144
    Prev
    Next
    INDEX
    Explanations

    adjective qualifiying noun/action

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

    This neuron fires on single, prominently capitalized tokens that serve as document or section headings (e.g. “City,” “Outlet,” “Online,” “Enterprise”).

    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
    long
    0.43
    、
    0.43
    type
    0.42
     и
    0.42
    node
    0.41
    types
    0.41
     및
    0.39
    ба
    0.39
     、
    0.38
    mic
    0.38
    POSITIVE LOGITS
     only
    0.47
     biologists
    0.46
     Artinya
    0.45
     PDFs
    0.44
     Ants
    0.44
     Idha
    0.43
     Antony
    0.42
     MPs
    0.42
     eivät
    0.42
     Digests
    0.42
    Activations Density 0.000%

    No Known Activations