© 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. 22-GEMMASCOPE-RES-131K
    7. 14256
    Prev
    Next
    INDEX
    Explanations

    pronoun subject followed by verb

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

    This neuron primarily detects the standalone pronoun “it.”

    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
     also
    -1.35
    これらの
    -0.98
    Condol
    -0.97
    also
    -0.89
    lor
    -0.89
     did
    -0.86
    in
    -0.84
     их
    -0.82
    Also
    -0.81
    それを
    -0.81
    POSITIVE LOGITS
     bowiem
    0.97
    饴
    0.94
     trám
    0.94
     dankbar
    0.92
     toolStrip
    0.92
     hilfreich
    0.91
    смотрите
    0.90
     vorgenommen
    0.88
    oved
    0.88
     giocatori
    0.87
    Activations Density 0.130%

    No Known Activations