© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43519
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
     not
    -1.74
     will
    -1.72
     Only
    -1.55
     an
    -1.51
     about
    -1.46
    le
    -1.45
     is
    -1.42
     usually
    -1.41
     generally
    -1.41
     ONLY
    -1.39
    POSITIVE LOGITS
     炖
    1.79
    ❔
    1.75
     maniere
    1.60
    mittelt
    1.58
    ㍑
    1.52
    衄
    1.51
     zdroj
    1.49
    愀
    1.48
     créer
    1.47
     vermel
    1.45
    Activations Density 0.017%

    No Known Activations