© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40674
    Prev
    Next
    INDEX
    Explanations

    baked goods like muffins and cake

    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
    呖
    -1.43
     dirige
    -1.37
     alemanes
    -1.35
     avantaj
    -1.34
    坐着
    -1.30
    f
    -1.30
     mexicanos
    -1.29
    鷽
    -1.28
    m
    -1.28
     ветер
    -1.28
    POSITIVE LOGITS
    dali
    1.52
     }}=
    1.47
    }$.
    1.45
    ＄
    1.42
    chequer
    1.41
    isSuccessful
    1.38
     We
    1.35
    PerformLayout
    1.34
    dä
    1.32
    引言
    1.31
    Activations Density 0.019%

    No Known Activations