© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4548
    Prev
    Next
    INDEX
    Explanations

    I want / I'm

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

    This neuron responds to isolated first-person self-references, especially the pronoun “I” (and its contracted forms).

    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
    .
    0.69
    ;
    0.64
     selaku
    0.62
     as
    0.61
    ↵
    0.54
     secondly
    0.53
    );
    0.53
    ।
    0.53
     for
    0.52
     。
    0.52
    POSITIVE LOGITS
     freien
    0.67
     ইলেক্ট্রোড
    0.65
     терро
    0.64
     ইলেক্ট্রো
    0.63
    ология
    0.62
     سرطان
    0.62
    ﺒ
    0.61
     एक्चु
    0.61
    Celltype
    0.61
    ﯿ
    0.60
    Activations Density 0.079%

    No Known Activations