© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    championship title or belt

    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
     Ô
    -1.72
    ︕
    -1.66
    꾼
    -1.59
     comprenant
    -1.55
    Ў
    -1.54
     wilfully
    -1.52
    (<
    -1.51
    本章未完
    -1.46
    ρους
    -1.45
    ?
    -1.44
    POSITIVE LOGITS
     without
    1.83
     before
    1.66
    ですので
    1.45
     has
    1.40
     until
    1.39
    ックス
    1.34
     feiert
    1.34
    ：[
    1.32
    なのですが
    1.32
     not
    1.32
    Activations Density 0.015%

    No Known Activations