© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129009
    Prev
    Next
    INDEX
    Explanations

    his followed by nouns

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

    This neuron detects occurrences of the masculine possessive pronoun “his.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -2.97
    让她
    -2.17
    里有
    -2.16
    捽
    -2.13
    来自于
    -2.13
    redientes
    -2.09
    鷓
    -2.08
    让他
    -2.06
    合约
    -2.03
    その他
    -2.02
    POSITIVE LOGITS
    it
    2.67
    {
    2.67
    1
    2.66
    is
    2.63
     own
    2.52
    y
    2.47
    这种
    2.44
     ‘
    2.42
     `
    2.41
     Such
    2.36
    Activations Density 0.075%

    No Known Activations