© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8875
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    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
     сейчас
    -1.46
     and
    -1.35
    湘南
    -1.32
     без
    -1.29
     Kriege
    -1.28
     &
    -1.26
    توضیحات
    -1.23
     Для
    -1.23
     insanların
    -1.21
     resistir
    -1.20
    POSITIVE LOGITS
    4
    1.30
     jednej
    1.27
    3
    1.25
    ⌗
    1.23
    =[];
    
    1.23
     indicato
    1.22
     vouloir
    1.15
    ][]
    1.13
     divertente
    1.13
     dicendo
    1.13
    Activations Density 0.023%

    No Known Activations