© 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. 10-GEMMASCOPE-RES-131K
    7. 24
    Prev
    Next
    INDEX
    Explanations

    Air Force

    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_10/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
     Она
    -2.48
    '
    -2.44
     двумя
    -2.31
     飯店
    -2.31
     However
    -2.30
     навіть
    -2.22
    寕
    -2.20
    つまり
    -2.19
    それにしても
    -2.19
    colgante
    -2.16
    POSITIVE LOGITS
     și
    2.14
    ATTLE
    2.13
    un
    2.09
    呖
    2.08
     ouverture
    2.06
    ઁ
    2.06
    絰
    2.05
    us
    2.03
    퐶
    2.00
    da
    1.99
    Activations Density 0.005%

    No Known Activations