© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65298
    Prev
    Next
    INDEX
    Explanations

    seat selection or ticket

    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
    RetentionPolicy
    -0.80
     кровать
    -0.78
    loan
    -0.77
    廠
    -0.75
     грудь
    -0.75
    🩲
    -0.73
    getTask
    -0.73
    ashian
    -0.73
    ̞
    -0.73
    publique
    -0.72
    POSITIVE LOGITS
     seat
    3.14
     seats
    3.05
    Seat
    2.41
    seat
    2.39
     seating
    2.31
     Seat
    2.23
    Seats
    2.19
     Seats
    2.09
    seats
    2.09
     ticket
    1.80
    Activations Density 0.009%

    No Known Activations