© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    rhythm and sedentary behavior

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

    The neuron strongly activates on occurrences of the word “rhythm” (e.g. “circadian rhythm,” musical rhythm, etc.).

    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
     is
    -2.98
     be
    -2.83
    呷
    -2.75
     trámites
    -2.73
     '
    -2.72
     he
    -2.70
    饪
    -2.63
     empleos
    -2.53
     requerimientos
    -2.53
    ſſen
    -2.52
    POSITIVE LOGITS
    If
    3.03
    你
    2.83
    that
    2.69
     Possibly
    2.67
    袮
    2.66
    When
    2.64
    ){
    2.56
     که
    2.39
    During
    2.38
     sebagaimana
    2.38
    Activations Density 0.008%

    No Known Activations