© 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. 9817
    Prev
    Next
    INDEX
    Explanations

    Bollywood films, actors, stars

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

    The neuron fires strongly on mentions of “Bollywood” (and closely related Indian‐film‐industry terms).

    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
     или
    -2.86
    ;
    -2.61
     یا
    -2.53
     Even
    -2.48
    !!!!!
    -2.47
    To
    -2.39
     Although
    -2.36
     comprimidos
    -2.30
    It
    -2.30
    ).
    -2.28
    POSITIVE LOGITS
    没能
    2.56
     joyous
    2.45
    鹛
    2.36
     captivating
    2.27
     joyful
    2.23
    鸶
    2.20
    啻
    2.20
    奁
    2.19
    ⤦
    2.17
     marvelous
    2.16
    Activations Density 0.002%

    No Known Activations