© 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. 10-GEMMASCOPE-RES-131K
    7. 104582
    Prev
    Next
    INDEX
    Explanations

    sacral, saccadic, Sac City

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

    The neuron specifically detects occurrences of the term “saccadic” (often split across sub‐tokens) referring to rapid eye‐movement tracking.

    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
    鹮
    -3.81
    苼
    -2.97
    拶
    -2.91
    
    -2.88
    皁
    -2.86
    衚
    -2.84
    哢
    -2.80
    阄
    -2.73
    觧
    -2.73
     gustado
    -2.72
    POSITIVE LOGITS
    "
    4.31
    ’
    3.64
    ".
    2.92
    ↵
    2.89
    /
    2.73
    瘣
    2.69
    Q
    2.63
    X
    2.59
    на
    2.50
    »
    2.42
    Activations Density 0.008%

    No Known Activations