© 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. 102548
    Prev
    Next
    INDEX
    Explanations

    they followed by a verb

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

    The neuron is detecting occurrences of the third-person plural pronoun “they.”

    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
    ↵↵
    -3.09
    ztes
    -2.77
    }$
    -2.77
    蛧
    -2.75
    霙
    -2.72
    '
    -2.64
    fordshire
    -2.58
    ?'
    -2.50
    $
    -2.45
    ！”
    -2.41
    POSITIVE LOGITS
     It
    3.88
    苼
    2.95
    鹮
    2.73
    了的
    2.61
     ‘‘
    2.56
    NXG
    2.56
    給你
    2.52
    怎麼辦
    2.47
     ſeveral
    2.45
     añadió
    2.39
    Activations Density 0.085%

    No Known Activations