© 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. 71933
    Prev
    Next
    INDEX
    Explanations

    ipv4 and ipv6 addresses

    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
    们的
    -2.22
     With
    -2.20
     That
    -2.19
     Almost
    -2.13
    俪
    -2.09
    口气
    -1.96
    輒
    -1.89
     tingling
    -1.86
     Nearly
    -1.84
     because
    -1.82
    POSITIVE LOGITS
    as
    2.89
    of
    2.72
    ra
    2.48
     процедуры
    2.47
     wonderfully
    2.45
    最重要的
    2.45
     gruesome
    2.42
     ferocious
    2.41
    r
    2.39
    鈊
    2.39
    Activations Density 0.001%

    No Known Activations