© 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. 84851
    Prev
    Next
    INDEX
    Explanations

    my followed by a noun

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

    This neuron fires on uses of the first-person possessive “my” (often together with its following noun).

    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
     människor
    -1.72
     alterações
    -1.70
     frequentemente
    -1.70
    つも
    -1.60
    很想
    -1.57
    佯
    -1.57
     normalmente
    -1.56
     entsprechende
    -1.55
     geprü
    -1.52
     ‘‘
    -1.51
    POSITIVE LOGITS
     in
    1.75
     from
    1.70
     beserta
    1.68
    دانلود
    1.66
     they
    1.63
     when
    1.62
     vehemently
    1.59
     dikutip
    1.56
     mereka
    1.55
     an
    1.55
    Activations Density 0.051%

    No Known Activations