© 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. 118943
    Prev
    Next
    INDEX
    Explanations

    having or had

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

    The neuron activates on occurrences of the verb “have” (and its forms like “had,” “having,” “has”), flagging instances of that word.

    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
     Those
    -1.95
     provides
    -1.79
     was
    -1.79
     gave
    -1.78
     makes
    -1.77
     facilitates
    -1.71
     began
    -1.71
     During
    -1.70
     brings
    -1.70
     during
    -1.66
    POSITIVE LOGITS
    receive
    1.77
    
    1.70
    奁
    1.69
    theres
    1.68
     listes
    1.68
    
    1.65
    THERE
    1.63
    糶
    1.63
    considering
    1.61
    鹩
    1.61
    Activations Density 0.019%

    No Known Activations