© 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. 22235
    Prev
    Next
    INDEX
    Explanations

    test functions with `t *testing.T`

    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
     comienza
    -1.39
     occasional
    -1.38
     in
    -1.38
    更何况
    -1.38
     other
    -1.37
     большин
    -1.35
     his
    -1.34
     anstatt
    -1.34
     a
    -1.31
     OF
    -1.26
    POSITIVE LOGITS
    こんに
    1.83
    』、
    1.55
     çantası
    1.55
    Якщо
    1.47
     गणना
    1.46
     vendar
    1.46
    ทุก
    1.42
     CascadeType
    1.41
     wußte
    1.40
    إذا
    1.38
    Activations Density 0.012%

    No Known Activations