© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38825
    Prev
    Next
    INDEX
    Explanations

    data units or structures

    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
    给我
    -1.16
     rules
    -1.15
     toutes
    -1.09
    <eos>
    -1.09
     Это
    -1.08
    Slik
    -1.05
     моей
    -1.05
    问题的
    -1.05
    олові
    -1.05
    生きて
    -1.05
    POSITIVE LOGITS
    лага
    1.18
    鎚
    1.13
     on
    1.13
     which
    1.12
    lista
    1.07
     wła
    1.06
    ⑪
    1.03
    änderungen
    1.02
    事で
    1.02
    sobre
    1.02
    Activations Density 0.743%

    No Known Activations