© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12176
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron specifically fires on occurrences of the subject pronoun “I” (and to a lesser extent sentence-initial “he”), marking first-person narrative references.

    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
    には
    -1.13
     telah
    -1.05
     pengobatan
    -1.02
    ȍ
    -1.00
     memiliki
    -0.99
    ることができます
    -0.98
     having
    -0.98
     have
    -0.95
    年には
    -0.94
     bará
    -0.94
    POSITIVE LOGITS
     prepares
    1.43
     progresses
    1.30
     nears
    1.28
    ḿ
    1.25
     approaches
    1.24
     prepare
    1.21
     approached
    1.19
     attravers
    1.14
     approach
    1.13
    vermectin
    1.13
    Activations Density 0.022%

    No Known Activations