© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    other, followed by examples

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

    The neuron detects occurrences of the word “other.”

    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
    を読んで
    -2.00
    鄠
    -1.54
    퐼
    -1.52
    が上が
    -1.51
    </h1>
    -1.49
    ヨーロ
    -1.45
    鸶
    -1.44
    
    -1.44
    :],
    -1.43
    ched
    -1.41
    POSITIVE LOGITS
    .”
    1.63
    ↵↵
    1.63
    多
    1.63
     cbd
    1.58
     kurulan
    1.50
    '
    1.48
    非常
    1.47
    有
    1.46
     added
    1.44
     if
    1.42
    Activations Density 0.020%

    No Known Activations