© 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. 70113
    Prev
    Next
    INDEX
    Explanations

    look at

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

    This neuron activates on occurrences of “look” (and close synonyms like “peek”) in calls to examine or view something.

    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
    ecutive
    -0.91
     cercano
    -0.88
    pidos
    -0.86
     piatta
    -0.86
    lija
    -0.85
    rasta
    -0.85
     koniec
    -0.84
     Studie
    -0.84
     like
    -0.83
     outflow
    -0.83
    POSITIVE LOGITS
     at
    2.28
     into
    1.41
     inside
    1.38
     around
    1.35
    see
    1.13
     👀
    1.12
    around
    1.11
    look
    1.07
    inside
    1.02
     culturales
    1.00
    Activations Density 0.013%

    No Known Activations