© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79761
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by a noun

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

    The neuron is highly activated by possessive determiners (e.g. “his,” “its,” “their,” “my”) 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_22/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
    Faktor
    -1.20
    Economía
    -1.20
     acceptez
    -1.16
    Toutes
    -1.09
    Beaucoup
    -1.07
    的关键
    -1.05
    órica
    -1.04
    phia
    -1.03
    čne
    -1.02
    いてる
    -1.01
    POSITIVE LOGITS
     to
    1.34
     approach
    1.13
     offering
    1.10
     response
    1.09
    to
    1.09
    ’
    1.08
    =>"
    1.07
     its
    1.06
    cembre
    1.06
    '
    1.04
    Activations Density 0.038%

    No Known Activations