© 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. 117929
    Prev
    Next
    INDEX
    Explanations

    actor playing a role

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    るま
    -0.73
     للت
    -0.71
    uses
    -0.69
    iotic
    -0.69
    inkel
    -0.69
     bunun
    -0.68
    usen
    -0.68
     arrange
    -0.68
    using
    -0.67
    促进
    -0.66
    POSITIVE LOGITS
     playing
    3.59
     plays
    2.81
    playing
    2.77
    Playing
    2.75
     portray
    2.67
     play
    2.66
     played
    2.61
     portraying
    2.61
     portrayal
    2.58
     Playing
    2.31
    Activations Density 0.042%

    No Known Activations