© 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. 66171
    Prev
    Next
    INDEX
    Explanations

    reservations, doubts, concerns

    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
     bibliographies
    -0.89
     Lair
    -0.87
     bbc
    -0.84
    mentable
    -0.80
     và
    -0.79
    ceğine
    -0.77
     thù
    -0.77
    互
    -0.77
    Сообщение
    -0.75
     Intens
    -0.75
    POSITIVE LOGITS
     reservations
    4.47
     reservation
    3.25
    reservations
    3.20
     Reservations
    3.16
    Reservations
    2.97
    reservation
    2.63
     Reservation
    2.61
     concerns
    2.59
     reservas
    2.58
     doubts
    2.42
    Activations Density 0.052%

    No Known Activations