© 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. 10-GEMMASCOPE-RES-131K
    7. 59989
    Prev
    Next
    INDEX
    Explanations

    "I" followed by verbs

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

    The neuron fires on occurrences of the first‐person 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
     of
    -2.72
    D
    -2.27
     also
    -2.27
    U
    -2.05
    },
    -2.02
    —
    -2.02
     -
    -1.98
    </sup>
    -1.98
     –
    -1.98
    </u>
    -1.96
    POSITIVE LOGITS
    takings
    2.03
    儼
    1.98
    НЫЙ
    1.84
    ῞
    1.74
    
    1.70
    
    1.67
     linke
    1.66
     Obras
    1.66
    鹉
    1.64
    蚍
    1.64
    Activations Density 0.131%

    No Known Activations