© 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. 70083
    Prev
    Next
    INDEX
    Explanations

    highline, air sorting, golf is

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

    The neuron specifically detects occurrences of the term “highline.”

    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
    0
    -3.75
    1
    -2.69
     unrelenting
    -2.63
    Although
    -2.53
    ↵↵
    -2.42
    Surprisingly
    -2.42
    Unlike
    -2.38
    Here
    -2.36
     Surprisingly
    -2.27
     what
    -2.23
    POSITIVE LOGITS
    幛
    2.94
    瓛
    2.89
    
    2.81
    ;"
    2.73
    睃
    2.70
    𓆏
    2.64
    赑
    2.64
    ,;
    2.61
    苼
    2.59
    튿
    2.59
    Activations Density 0.000%

    No Known Activations