© 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. 98639
    Prev
    Next
    INDEX
    Explanations

    looking for or to

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

    The neuron detects occurrences of the verb “look” (in forms like look, looking, looked) in the text.

    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
    卺
    -0.98
    傚
    -0.95
    为止
    -0.92
     mej
    -0.91
     válvula
    -0.90
    艫
    -0.89
     озна
    -0.89
     tervez
    -0.87
    
    -0.86
    nological
    -0.85
    POSITIVE LOGITS
     to
    2.95
     toward
    1.93
     towards
    1.76
     beyond
    1.38
     upon
    1.13
     към
    1.04
     for
    1.03
    toward
    1.02
     inward
    1.02
     hacia
    0.94
    Activations Density 0.016%

    No Known Activations