© 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. 10-GEMMASCOPE-RES-131K
    7. 20148
    Prev
    Next
    INDEX
    Explanations

    in: or before judges

    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
     hectáreas
    -1.78
     our
    -1.55
    هدف
    -1.52
    蟊
    -1.52
     telefoon
    -1.52
     mogelijkheid
    -1.51
     și
    -1.50
     danych
    -1.49
     afbeelding
    -1.48
     AÑOS
    -1.48
    POSITIVE LOGITS
    ↵
    1.50
    РЫ
    1.49
     by
    1.47
    所以在
    1.43
     there
    1.38
     使っ
    1.38
    <?
    1.37
    嗡
    1.33
     выбирать
    1.32
     in
    1.31
    Activations Density 0.005%

    No Known Activations