© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71291
    Prev
    Next
    INDEX
    Explanations

    for or at

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

    The neuron consistently activates on occurrences of the word “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
    是
    -2.88
    的
    -2.84
    ﮏ
    -2.78
    人の
    -2.75
    ﮑ
    -2.72
    Rptr
    -2.64
    z
    -2.59
    一個
    -2.52
    法國
    -2.50
     頂
    -2.50
    POSITIVE LOGITS
    摇了
    2.77
     We
    2.69
    鸶
    2.50
    盦
    2.47
    尛
    2.47
    弍
    2.42
    へ行
    2.34
    结语
    2.34
    an
    2.33
    を変える
    2.33
    Activations Density 0.015%

    No Known Activations