© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4465
    Prev
    Next
    INDEX
    Explanations

    looks intently

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

    The neuron fires on verbs and verb forms that denote looking or visually focusing (e.g. looked, looking, stared, gazed).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    1.06
    er
    0.84
     nemen
    0.79
     bruke
    0.78
     autores
    0.77
     chu
    0.77
     GSM
    0.76
    ir
    0.76
     using
    0.76
     XLR
    0.75
    POSITIVE LOGITS
    了一眼
    0.97
     totalSupply
    0.81
    лян
    0.75
     intently
    0.75
    ョ
    0.74
    角落
    0.73
    ónde
    0.72
    瞍
    0.72
     gazing
    0.72
    一眼
    0.70
    Activations Density 0.065%

    No Known Activations