© 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. 128447
    Prev
    Next
    INDEX
    Explanations

    leisure and entertainment keywords

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

    The neuron fires strongly on nouns naming leisure or entertainment activities and consumable “fun” items—e.g. pot, art, board games, cards, TV, music, videos, sports, alcoholic beverages, cigarettes.

    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
     but
    -1.57
    )
    -1.37
     enfermed
    -1.28
    -“
    -1.26
    ISSUES
    -1.23
    mann
    -1.22
    ing
    -1.21
    ଼
    -1.21
    :
    -1.21
    ala
    -1.20
    POSITIVE LOGITS
     from
    1.59
     on
    1.48
     singur
    1.36
     destacados
    1.34
    uties
    1.30
     vitória
    1.29
     aliento
    1.29
     bautizo
    1.27
    と同じ
    1.27
     like
    1.27
    Activations Density 0.243%

    No Known Activations