© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    CEO or president of

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

    The neuron primarily activates on capitalized organizational or official role titles (e.g. CEO, Chairman, Secretary, President).

    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
     একটা
    0.61
    ไหน
    0.54
     которое
    0.53
    ḳ
    0.53
    温度
    0.52
    溫度
    0.52
    Humidity
    0.52
    szág
    0.52
    Чтобы
    0.50
    彡
    0.49
    POSITIVE LOGITS
     of
    0.95
     ofthe
    0.86
     della
    0.76
     emeritus
    0.73
     της
    0.70
     của
    0.68
     directeur
    0.66
     Emeritus
    0.63
     Director
    0.62
     and
    0.61
    Activations Density 0.020%

    No Known Activations