© 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. 31-GEMMASCOPE-2-RES-16K
    4. 7977
    Prev
    Next
    INDEX
    Explanations

    docker images and medical conditions

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

    The neuron strongly activates on domain-specific service or industry nouns (e.g. “Legal,” “Cruise,” “plumbing,” “dental,” “security”) and is thus detecting professional or commercial category terms.

    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
    などの
    0.66
    とか
    0.65
    Jenkins
    0.63
    、
    0.59
    など
    0.59
    MyAdmin
    0.58
    মূলক
    0.57
     येथील
    0.56
     وغیرہ
    0.56
    Marco
    0.56
    POSITIVE LOGITS
    দ্রোহ
    0.66
    쁠
    0.64
    તના
    0.62
     principi
    0.61
    withtag
    0.61
     filozof
    0.61
     illiterate
    0.59
     kontinu
    0.59
     experimentado
    0.59
     mixto
    0.59
    Activations Density 0.734%

    No Known Activations