© 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. 69033
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron is looking for third-person singular masculine pronouns (especially “he”).

    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
     ditemui
    -1.55
     prisonniers
    -1.44
    Incluso
    -1.37
    ранее
    -1.30
     jedoch
    -1.30
    ⃛
    -1.28
    ㆁ
    -1.27
     yani
    -1.26
     préfé
    -1.26
     misalnya
    -1.23
    POSITIVE LOGITS
    \
    1.88
    "
    1.50
    '
    1.45
        
    1.41
     answers
    1.37
    上の
    1.36
     inyección
    1.36
                               
    1.36
     Φ
    1.34
     další
    1.34
    Activations Density 0.038%

    No Known Activations