© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1621
    Prev
    Next
    INDEX
    Explanations

    possessives followed by own or custom

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

    The neuron fires on possessive pronouns (e.g. your, his, her, their) indicating ownership.

    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
    "
    -2.50
     violenta
    -1.62
     blanda
    -1.62
     ceramica
    -1.59
     уровня
    -1.58
    ！"
    -1.55
    咐
    -1.54
    two
    -1.52
    among
    -1.51
     stava
    -1.48
    POSITIVE LOGITS
     own
    1.91
     then
    1.66
     of
    1.62
    loja
    1.55
    𐌸
    1.50
     It
    1.48
     also
    1.48
    projeto
    1.47
    ourcen
    1.41
    iences
    1.39
    Activations Density 0.053%

    No Known Activations