© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    look and how it's used

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

    The neuron activates on occurrences of the verb “look” (in any form or tense).

    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
     when
    -2.47
     after
    -2.09
     that
    -2.09
    quelize
    -2.06
    quetas
    -2.02
     during
    -1.90
    ólogos
    -1.87
    vanju
    -1.87
    yakit
    -1.78
     until
    -1.76
    POSITIVE LOGITS
    {
    1.91
    ка
    1.66
                     
    1.63
            
    1.61
    Compared
    1.60
    </h5>
    1.56
     COULD
    1.55
                        
    1.54
      
    1.52
                               
    1.47
    Activations Density 0.005%

    No Known Activations