© 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. 66981
    Prev
    Next
    INDEX
    Explanations

    `you` followed by verbs

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

    The neuron strongly activates on the second‐person pronoun “you,” i.e. direct addresses to the reader or listener.

    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
     will
    -1.23
    zielle
    -1.09
    estroyer
    -0.95
     वाला
    -0.93
    Mascul
    -0.92
     stöd
    -0.91
    Decided
    -0.90
    єм
    -0.90
     который
    -0.90
     förra
    -0.90
    POSITIVE LOGITS
     see
    1.36
     guys
    1.27
     people
    1.18
     voient
    1.15
     hören
    1.12
    '
    1.09
     seen
    1.07
    ipot
    1.02
     horen
    1.02
     gerekir
    1.02
    Activations Density 0.037%

    No Known Activations