© 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. 58432
    Prev
    Next
    INDEX
    Explanations

    generics in programming code

    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
     Económica
    -1.55
     eit
    -1.52
     and
    -1.51
     eficientes
    -1.49
    🕗
    -1.48
     then
    -1.45
    Zubereitung
    -1.43
    〖
    -1.39
     vore
    -1.35
     nutz
    -1.34
    POSITIVE LOGITS
    1
    2.09
    2
    1.88
    ሖ
    1.72
    男主
    1.70
    8
    1.66
     einwand
    1.64
     miłości
    1.62
    ᠂
    1.59
    4
    1.55
    0
    1.53
    Activations Density 0.009%

    No Known Activations