© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on 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_31_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
    ceased
    0.57
    jaman
    0.54
    懋
    0.52
    boldsymbol
    0.50
    itektur
    0.49
    bels
    0.49
     организаций
    0.48
    баров
    0.48
    rally
    0.48
    த்துடன்
    0.48
    POSITIVE LOGITS
     copiar
    0.62
     (!)
    0.61
     Restart
    0.58
     zurück
    0.57
     ອ
    0.57
     hehe
    0.56
    VideoStream
    0.56
     ⏮
    0.56
     videot
    0.56
     düşünüyorum
    0.55
    Activations Density 0.000%

    No Known Activations