© 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. 72520
    Prev
    Next
    INDEX
    Explanations

    CPU instruction sets (MMX, SSE, AVX)

    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
     in
    -2.06
     also
    -1.70
     It
    -1.70
     walaupun
    -1.57
     to
    -1.55
     maksud
    -1.49
     if
    -1.48
     kecuali
    -1.48
     meneg
    -1.46
    がついて
    -1.45
    POSITIVE LOGITS
    ↵↵
    2.36
    quilo
    1.70
    ۀ
    1.46
     remarqué
    1.46
    肆
    1.42
    ζ
    1.39
    _
    1.38
    .
    1.37
    和
    1.37
    al
    1.35
    Activations Density 0.003%

    No Known Activations