© 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. 34-GEMMASCOPE-RES-131K
    7. 31522
    Prev
    Next
    INDEX
    Explanations

    result / output

    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_34/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
     dispuestos
    -0.98
    امه
    -0.90
    Summing
    -0.83
    なのは
    -0.82
     interesados
    -0.81
     sicherzustellen
    -0.81
     ausgesprochen
    -0.79
     گذشت
    -0.78
    是一個
    -0.78
     weiterhin
    -0.77
    POSITIVE LOGITS
     result
    1.37
     результа
    1.35
    result
    1.21
     результат
    1.18
     결과
    1.16
     results
    1.15
    Result
    1.10
     Result
    1.09
    resultat
    1.01
    結果
    0.98
    Activations Density 0.024%

    No Known Activations