© 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. 9359
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on tokens that are parts of named entities—especially company names and associated numeric or financial figures.

    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
     pesantren
    0.73
     lesbians
    0.71
    m
    0.69
     netizens
    0.69
     gays
    0.68
     helpline
    0.67
    0.67
    ם
    0.67
     ಹಾಕ
    0.64
    ない
    0.64
    POSITIVE LOGITS
    ち
    0.66
     acqua
    0.66
    olução
    0.64
    鶘
    0.64
    ̣ng
    0.64
    餬
    0.64
    であり
    0.61
    ύτε
    0.61
    Beverungen
    0.61
    cci
    0.61
    Activations Density 21.389%

    No Known Activations