© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49695
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun and subsequent noun

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

    The neuron strongly activates on possessive pronouns (e.g. ‘her’, ‘their’, ‘your’) indicating ownership or association.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     тща
    -0.91
    dote
    -0.86
     resides
    -0.85
    हर
    -0.81
     Ona
    -0.79
    </h1>
    -0.79
    ortium
    -0.78
     chimiques
    -0.78
    ambiguation
    -0.78
    视线
    -0.78
    POSITIVE LOGITS
     surroundings
    2.02
     own
    1.67
     options
    1.54
     limitations
    1.34
     mistakes
    1.27
     opportunities
    1.27
     obligations
    1.27
     environment
    1.26
     limitaciones
    1.23
     Surround
    1.18
    Activations Density 0.046%

    No Known Activations