© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    specific numbers, quantities, or symbols

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

    The neuron primarily detects occurrences of the standalone first-person pronoun “I.”

    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
    ،
    0.71
    embedding
    0.67
    ێن
    0.66
    ,
    0.64
     encaps
    0.64
    controls
    0.63
    اموش
    0.62
    erst
    0.61
    Mua
    0.61
    getLast
    0.60
    POSITIVE LOGITS
    야
    0.89
     concussion
    0.84
     gag
    0.82
    蛲
    0.80
     broth
    0.80
     група
    0.80
     数据
    0.79
     विपक्षी
    0.79
     служба
    0.79
    펭
    0.78
    Activations Density 0.000%

    No Known Activations