© 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. 59313
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

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

    The neuron consistently activates on the first‐person singular pronoun “I.”

    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
     protectora
    -2.02
    痼
    -1.97
    ˼
    -1.88
    
    -1.88
     casada
    -1.84
     Američ
    -1.83
     encargada
    -1.83
     pelig
    -1.83
     even
    -1.81
    
    -1.80
    POSITIVE LOGITS
    v
    1.96
    -
    1.96
    1
    1.96
    tr
    1.85
    z
    1.84
    oo
    1.81
    vin
    1.79
    as
    1.79
    om
    1.77
    los
    1.71
    Activations Density 0.011%

    No Known Activations