© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    cost, price, value, questions, schema

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

    The neuron fires strongly on standalone resource‐label headings (e.g. “Website,” “Official site,” “Information site,” “Sale price,” “Message”) that introduce or label sections.

    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
    '
    0.52
    ("
    0.47
    (
    0.47
    ${
    0.47
     ihe
    0.47
    <start_of_image>
    0.46
    Chan
    0.45
    Neg
    0.45
    Weather
    0.45
    \'{
    0.45
    POSITIVE LOGITS
     für
    0.72
     från
    0.72
     untuk
    0.69
     for
    0.68
     fürs
    0.66
    ındaki
    0.64
     для
    0.64
     för
    0.64
     pentru
    0.63
     द्वारा
    0.60
    Activations Density 0.001%

    No Known Activations