© 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. 22-GEMMASCOPE-RES-131K
    7. 34058
    Prev
    Next
    INDEX
    Explanations

    third person pronoun followed by verb

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

    The neuron primarily activates on sentence-initial third-person subject pronouns (e.g., “He,” “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_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
    Давайте
    -1.55
     כאשר
    -1.49
     также
    -1.40
     również
    -1.27
    Sommaire
    -1.26
    このような
    -1.21
     Также
    -1.19
     birçok
    -1.16
     they
    -1.13
     також
    -1.13
    POSITIVE LOGITS
     rasch
    1.27
     too
    1.16
     not
    1.14
    Ĝ
    1.09
    Ď
    1.07
     none
    1.07
    object
    1.06
     needn
    1.05
    uiente
    1.05
     no
    1.05
    Activations Density 0.057%

    No Known Activations