© 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. 34-GEMMASCOPE-RES-131K
    7. 106640
    Prev
    Next
    INDEX
    Explanations

    play followed by noun

    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
     آش
    -0.78
     explorations
    -0.71
     зале
    -0.70
     exploring
    -0.67
     scolaires
    -0.66
     consortium
    -0.66
     عش
    -0.66
     Tempe
    -0.65
    ELY
    -0.64
    Cabe
    -0.64
    POSITIVE LOGITS
     play
    4.72
    play
    3.66
    Play
    3.25
     Play
    3.06
     PLAY
    2.70
    PLAY
    2.59
    プレイ
    2.05
     plays
    1.78
     spielen
    1.70
    plays
    1.64
    Activations Density 0.039%

    No Known Activations