© 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. 34-GEMMASCOPE-RES-131K
    7. 30478
    Prev
    Next
    INDEX
    Explanations

    class declarations

    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_34/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
     hoping
    -0.89
     容量
    -0.82
     except
    -0.79
    dań
    -0.74
    ็อ
    -0.74
    RectangleBorder
    -0.74
    矩
    -0.73
    逢
    -0.72
     Weh
    -0.72
     Eiffel
    -0.71
    POSITIVE LOGITS
     class
    1.63
    class
    1.36
    [].
    0.94
     osztály
    0.85
     Klasse
    0.83
     ""}
    0.82
     sınıf
    0.80
    ਖ਼
    0.80
     classes
    0.79
     Kommunikation
    0.78
    Activations Density 0.006%

    No Known Activations