© 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. 39239
    Prev
    Next
    INDEX
    Explanations

    mine and yours

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

    The neuron is specially sensitive to personal possessive pronouns indicating ownership—especially “mine” (and related forms like “yours”).

    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
     meisje
    -1.58
     保護
    -1.57
     Jérusalem
    -1.55
     Holanda
    -1.55
    镲
    -1.53
    ܜ
    -1.52
    蔟
    -1.49
     違い
    -1.48
    hiva
    -1.48
    らの
    -1.46
    POSITIVE LOGITS
    ll
    1.82
    ––
    1.81
     were
    1.78
    is
    1.61
    m
    1.59
     wasn
    1.47
     gestaltet
    1.47
     doloroso
    1.47
    普通的
    1.45
     esté
    1.44
    Activations Density 0.011%

    No Known Activations