© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3183
    Prev
    Next
    INDEX
    Explanations

    places, organizations, and professions

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

    The neuron is specialized to detect proper‐named organizations or institution names.

    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
    世界の
    0.56
    🌐
    0.56
    类型
    0.55
    中国的
    0.55
    חות
    0.54
    美国的
    0.54
    ocracy
    0.51
    🕋
    0.51
    Philippines
    0.50
    菲律
    0.50
    POSITIVE LOGITS
     teenager
    0.77
     employee
    0.72
     직원
    0.70
     staffers
    0.69
     economist
    0.68
     vocalist
    0.68
     drummer
    0.68
     goalkeeper
    0.68
     outfielder
    0.68
     कर्मचारी
    0.65
    Activations Density 0.001%

    No Known Activations