© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130177
    Prev
    Next
    INDEX
    Explanations

    look at something

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

    The neuron strongly activates on occurrences of the word “look,” especially in phrases like “a look at,” “in-depth look,” or “look into.”

    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
    鱻
    -1.80
     Empieza
    -1.80
    عنی
    -1.67
    緜
    -1.67
    後期
    -1.66
     สำหรับ
    -1.65
     Profitez
    -1.63
    </sub>
    -1.57
     disregarding
    -1.57
    lgari
    -1.56
    POSITIVE LOGITS
    d
    2.33
    v
    1.94
    ches
    1.88
     !!!!
    1.84
    8
    1.81
    !!!!!!
    1.74
    全都
    1.70
    !!!!!!!!
    1.70
    ant
    1.69
     pals
    1.65
    Activations Density 0.017%

    No Known Activations