© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    people nearby

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

    This neuron fires on first‐person narrative elements—personal pronouns and references (like “I,” “me,” “my,” and related mentions of others in the speaker’s immediate experience).

    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
     annuity
    0.74
     ক্ষত
    0.74
     ductility
    0.73
    ləşdir
    0.71
    鏻
    0.71
     renewable
    0.70
     restructure
    0.68
    甙
    0.68
     morphogenesis
    0.65
    兑
    0.64
    POSITIVE LOGITS
     nearby
    1.26
     neighboring
    1.26
     neighbors
    1.22
     neighbours
    1.18
     neighbouring
    1.16
    Nearby
    1.16
     сосе
    1.15
     neighbor
    1.13
     Nearby
    1.12
    nearby
    1.11
    Activations Density 1.358%

    No Known Activations