© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13316
    Prev
    Next
    INDEX
    Explanations

    hero, fort, ion tail, Dan Geer, GDP per capita, entry-level, root

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

    This neuron fires on prominent category or section‐heading terms—i.e. key nouns or labels (often proper names or important domain headings) that introduce new sections or 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_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
     fordi
    0.63
     [
    0.54
     voor
    0.54
     chars
    0.54
     (
    0.54
     which
    0.54
     meanwhile
    0.54
     y
    0.52
     inzwischen
    0.52
     hvis
    0.51
    POSITIVE LOGITS
    ढ़े
    0.70
    glied
    0.67
    㛺
    0.66
    kaç
    0.65
     अराउंड
    0.64
     alguém
    0.63
    íng
    0.63
    agré
    0.62
    intă
    0.61
    снаб
    0.61
    Activations Density 0.554%

    No Known Activations