© 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. 22-GEMMASCOPE-RES-131K
    7. 34044
    Prev
    Next
    INDEX
    Explanations

    Proton pump Unix paths

    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_22/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
     so
    -1.16
     både
    -0.93
     not
    -0.93
     farmacé
    -0.91
    Là
    -0.91
    وكان
    -0.90
     especially
    -0.86
    特別
    -0.85
     utafiti
    -0.85
    ствий
    -0.85
    POSITIVE LOGITS
     but
    0.96
    がありますが
    0.95
    但是在
    0.95
    但在
    0.94
    вед
    0.90
     появится
    0.90
     NSCoder
    0.88
    よい
    0.85
     makhluk
    0.84
    melidir
    0.83
    Activations Density 0.011%

    No Known Activations