© 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. 111277
    Prev
    Next
    INDEX
    Explanations

    fatigue after

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

    The neuron activates for the word "fatigue" and related terms in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect occurrences of the word “fatigue.”

    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
    噥
    -2.77
    盌
    -2.67
    もの
    -2.67
     complimented
    -2.64
    谖
    -2.63
     puntata
    -2.58
     But
    -2.55
    ⓷
    -2.50
    憍
    -2.48
     dubbed
    -2.45
    POSITIVE LOGITS
    e
    2.72
    心の
    2.27
    ーい
    2.27
    b
    2.27
    いろいろ
    2.20
    its
    2.09
    ときに
    2.08
    w
    2.08
    izing
    2.08
     In
    2.08
    Activations Density 0.004%

    No Known Activations