© 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. 10-GEMMASCOPE-RES-131K
    7. 19867
    Prev
    Next
    INDEX
    Explanations

    start of clause with pronoun

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

    This neuron responds to the very first word of a sentence (i.e. sentence-initial tokens).

    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
     événement
    -1.82
    
    -1.66
     Vrbo
    -1.63
    𝅥
    -1.63
     corriger
    -1.63
    eses
    -1.63
     moſt
    -1.63
     墊
    -1.61
    ---->
    -1.60
    킁
    -1.60
    POSITIVE LOGITS
     it
    2.09
    ↵
    2.02
    </b>
    1.94
    :
    1.86
     new
    1.78
    </h2>
    1.66
    ),
    1.61
    ).
    1.57
     recently
    1.57
     recent
    1.56
    Activations Density 0.382%

    No Known Activations