© 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. 116730
    Prev
    Next
    INDEX
    Explanations

    pay attention or acquire

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

    This neuron activates on the word “eye” (and its plural “eyes”), especially in contexts like “keep an eye out/on,” marking references to watching or monitoring.

    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
    cá
    -1.02
    ัด
    -0.84
    ustering
    -0.81
    观看
    -0.80
    iration
    -0.80
    şağı
    -0.79
    вот
    -0.79
    FromJson
    -0.78
    tellingen
    -0.78
    chiede
    -0.78
    POSITIVE LOGITS
     on
    1.58
     open
    0.91
     things
    0.84
    things
    0.82
    Open
    0.82
    開放
    0.81
     proceedings
    0.80
    open
    0.78
     otev
    0.78
     druž
    0.77
    Activations Density 0.010%

    No Known Activations