© 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. 22-GEMMASCOPE-RES-131K
    7. 66787
    Prev
    Next
    INDEX
    Explanations

    macro, doctype, andcode starts

    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
     not
    -0.97
    beforeAll
    -0.86
     piden
    -0.83
    Metallica
    -0.79
    fetchAll
    -0.79
    Jungkook
    -0.78
    SUND
    -0.78
     нача
    -0.77
     amenaz
    -0.77
    hpp
    -0.76
    POSITIVE LOGITS
    どれ
    1.09
    營業
    0.93
    找个
    0.92
     někter
    0.90
     someone
    0.90
     kolejne
    0.88
    チーフ
    0.85
     名前
    0.84
    romolecules
    0.83
     τελευτα
    0.82
    Activations Density 0.004%

    No Known Activations