© 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. 123955
    Prev
    Next
    INDEX
    Explanations

    letter or 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_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
    沨
    -2.31
    ↵
    -2.17
     großen
    -2.08
     vorigen
    -2.06
     unserem
    -1.93
    indest
    -1.92
     neuen
    -1.88
    诨
    -1.84
     schwere
    -1.84
    滁
    -1.83
    POSITIVE LOGITS
    ™.
    2.69
    .
    2.64
    ''.
    2.48
    。
    2.48
    鈥
    2.45
     Garantía
    2.39
    ;.
    2.38
    ․
    2.36
    ers
    2.34
    .",
    2.33
    Activations Density 0.006%

    No Known Activations