© 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. 59359
    Prev
    Next
    INDEX
    Explanations

    wake up, wakefulness, sleep cycles

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

    The neuron detects the word "Wake" especially when referring to proper nouns like "Wake Forest," "Wake County," or "WakeMed."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    "
    -3.44
    '
    -3.41
    ,"
    -3.41
    re
    -3.28
     has
    -3.05
    ],
    -2.89
     "
    -2.84
     echten
    -2.59
    },
    -2.56
    .,
    -2.41
    POSITIVE LOGITS
    鵟
    2.70
    ꯸
    2.63
    Semua
    2.59
    笮
    2.56
    刘
    2.55
    咘
    2.52
    Sebelum
    2.50
    Цены
    2.42
    Kelebihan
    2.36
    蘩
    2.36
    Activations Density 0.006%

    No Known Activations