© 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. 73450
    Prev
    Next
    INDEX
    Explanations

    programming syntax and punctuation

    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
    $
    -1.92
     this
    -1.91
    A
    -1.84
     three
    -1.71
     there
    -1.68
    He
    -1.63
    N
    -1.62
     two
    -1.58
     your
    -1.57
     waarvan
    -1.57
    POSITIVE LOGITS
     ‚
    1.91
     Эти
    1.85
    chnung
    1.79
    賔
    1.77
    。　　
    1.72
     Internation
    1.70
    我这
    1.67
    苼
    1.67
    呿
    1.64
    婬
    1.63
    Activations Density 0.001%

    No Known Activations