© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58320
    Prev
    Next
    INDEX
    Explanations

    gaze and sight direction

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

    The neuron activates on occurrences of “gaze” and related eye‐looking words (e.g. stare, gazing, looking), flagging references to where or how someone is looking.

    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
    }$
    -2.77
    ים
    -2.39
     čís
    -2.17
    state
    -2.11
    atação
    -2.06
    荩
    -2.06
    🫔
    -1.98
    づき
    -1.97
     intending
    -1.95
     Either
    -1.94
    POSITIVE LOGITS
     thc
    2.48
    o
    2.33
    5
    2.28
    ⩥
    2.20
    7
    2.13
    因为他
    2.03
    n
    1.99
     ihe
    1.98
    一個
    1.96
    9
    1.95
    Activations Density 0.001%

    No Known Activations