© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9304
    Prev
    Next
    INDEX
    Explanations

    His

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

    This neuron detects possessive pronouns (e.g., “his,” “my,” “its”).

    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
     DoD
    0.64
     способны
    0.59
     здо
    0.59
    ጄ
    0.59
    ⅾ
    0.58
     Catalog
    0.58
     オン
    0.57
    唳
    0.56
     Lung
    0.56
     piper
    0.56
    POSITIVE LOGITS
     proponents
    0.59
     customers
    0.57
     forefathers
    0.54
     którego
    0.54
     regiment
    0.53
    Seventh
    0.53
    犠
    0.53
    His
    0.52
    “
    0.52
    troops
    0.52
    Activations Density 0.010%

    No Known Activations