© 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. 10-GEMMASCOPE-RES-131K
    7. 14729
    Prev
    Next
    INDEX
    Explanations

    doc followed by other words

    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
    Ⲉ
    -2.88
    ⬯
    -2.52
    苹
    -2.52
    籐
    -2.50
     různ
    -2.47
     notable
    -2.45
    菔
    -2.44
    葳
    -2.42
    与此
    -2.30
     tématu
    -2.28
    POSITIVE LOGITS
    ’
    3.33
    的
    3.19
    l
    2.94
    ного
    2.83
    縂
    2.75
     殼
    2.44
    可
    2.41
    ed
    2.41
     cruda
    2.39
    庒
    2.31
    Activations Density 0.007%

    No Known Activations