© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7951
    Prev
    Next
    INDEX
    Explanations

    entities in interactions

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

    The neuron fires on singular nouns that label or identify the role or entity being acted upon (e.g. “holder,” “applicant,” “poster,” “recipient”).

    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
     અમારી
    0.83
     vores
    0.82
     आमच्या
    0.81
     μας
    0.81
     ہمارے
    0.78
     nossas
    0.78
    imizi
    0.78
     আমাদের
    0.77
     અમારા
    0.76
    4
    0.75
    POSITIVE LOGITS
    前記
    0.69
    对象的
    0.67
     trở
    0.66
    将其
    0.65
    ผู
    0.65
     становится
    0.64
    或其他
    0.63
    是一位
    0.63
    IsMethod
    0.63
     distal
    0.60
    Activations Density 0.040%

    No Known Activations