© 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. 7127
    Prev
    Next
    INDEX
    Explanations

    uses or keeps

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

    This neuron fires on first-person personal narrative cues (e.g., “I,” “my,” “we,” and related self-referential actions).

    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
    あなたの
    0.80
    に対し
    0.78
    情報を
    0.78
     вашей
    0.77
    鈑
    0.76
    会社の
    0.75
    unternehmen
    0.75
    ําน
    0.74
    companies
    0.73
     государ
    0.73
    POSITIVE LOGITS
     uses
    0.82
    每次
    0.79
     (
    0.77
     used
    0.76
     giggle
    0.76
     Keeps
    0.75
     keeps
    0.74
     occasionally
    0.74
     use
    0.74
     inadvert
    0.73
    Activations Density 0.235%

    No Known Activations