© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    seat and its context

    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
    velocityY
    -0.71
    buquerque
    -0.70
     uovo
    -0.68
    Bonjour
    -0.67
    partials
    -0.67
     traduire
    -0.66
     EXAM
    -0.66
     Suffer
    -0.66
    komna
    -0.65
    dolu
    -0.65
    POSITIVE LOGITS
     seats
    5.94
     seat
    5.81
    seat
    4.25
     Seats
    4.19
    seats
    4.16
     Seat
    4.00
    Seat
    4.00
    Seats
    3.78
     seating
    3.63
     SEAT
    2.89
    Activations Density 0.053%

    No Known Activations