© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13366
    Prev
    Next
    INDEX
    Explanations

    also include

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

    The neuron strongly activates on first-person self‐references (especially the pronoun “I” and related “also” when describing one’s own 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
    :‏
    0.80
     teeming
    0.77
    леты
    0.77
     fréquemment
    0.76
    多彩
    0.73
     असंख्य
    0.73
     relentless
    0.72
     മുതല്‍
    0.71
     multimillion
    0.71
    oczes
    0.70
    POSITIVE LOGITS
     didnt
    0.85
    ก็
    0.77
    结尾
    0.77
     wasnt
    0.73
     +
    0.73
     (/
    0.73
    っぽい
    0.71
     (
    0.70
     (?)
    0.70
     didn
    0.69
    Activations Density 0.073%

    No Known Activations