© 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. 8118
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on named entities—proper nouns, dates, places, organizations, and other label-style tokens.

    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
    芒果
    0.71
    暨
    0.69
    ος
    0.69
    球员
    0.68
    -/
    0.66
     ಹಾಗೂ
    0.66
    肌肤
    0.65
    珠宝
    0.65
    ދ
    0.64
    畀
    0.63
    POSITIVE LOGITS
     microbes
    0.75
     OECD
    0.75
     supergiants
    0.72
     economists
    0.68
     argues
    0.67
     trillions
    0.66
     sinned
    0.66
     crises
    0.66
     undermines
    0.66
     profoundly
    0.65
    Activations Density 20.721%

    No Known Activations