© 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. 34-GEMMASCOPE-RES-131K
    7. 33086
    Prev
    Next
    INDEX
    Explanations

    words fitting "Sen"

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

    The neuron consistently fires on the three‐letter sequence “Sen” (i.e. the token “Sen” appearing as a prefix in words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    手間
    -0.77
     pursuits
    -0.75
    dicion
    -0.73
    程度上
    -0.73
    trar
    -0.72
    diseño
    -0.72
     endet
    -0.72
     teto
    -0.71
    anément
    -0.71
    いたしました
    -0.71
    POSITIVE LOGITS
     Sen
    1.88
    Sen
    1.67
     sen
    1.52
     SEN
    1.42
     senescence
    1.23
     SENS
    1.22
    sen
    1.18
     сен
    1.11
     Sene
    1.10
     Sena
    1.05
    Activations Density 0.020%

    No Known Activations