© 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. 34-GEMMASCOPE-RES-131K
    7. 31016
    Prev
    Next
    INDEX
    Explanations

    pronouns and "you"

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

    The neuron is highly sensitive to the colloquial second-person plural pronoun “y’all” (including its variants and capitalized forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     свои
    -0.97
    jarige
    -0.88
    rdoba
    -0.85
     kater
    -0.85
    忒
    -0.84
    ymm
    -0.83
     marav
    -0.82
     myst
    -0.82
     swoje
    -0.81
     sted
    -0.81
    POSITIVE LOGITS
     you
    1.20
     môžete
    0.98
    You
    0.98
     Significant
    0.91
    you
    0.91
    們
    0.91
    મે
    0.88
     have
    0.88
     anklicken
    0.88
     vocês
    0.87
    Activations Density 0.011%

    No Known Activations