© 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. 2925
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting direct second‐person address (e.g. “you,” “your,” “you’ll,” etc.).

    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
     लेते
    0.51
     chickens
    0.50
     vín
    0.50
    軾
    0.50
    徠
    0.50
     Dac
    0.50
     ው
    0.49
     troch
    0.49
    DropdownBox
    0.49
     offsetX
    0.48
    POSITIVE LOGITS
    <strong>
    0.56
    <
    0.52
     হত্যাকা
    0.50
    áll
    0.50
    ↵↵↵
    0.49
    मेलन
    0.48
    馮
    0.47
     upper
    0.47
     FAX
    0.47
    гел
    0.46
    Activations Density 0.057%

    No Known Activations