© 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. 73194
    Prev
    Next
    INDEX
    Explanations

    dropping off

    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
     一个
    -2.14
    而在
    -2.14
    =
    -2.11
    y
    -2.09
    냑
    -2.06
            
    -1.99
     而
    -1.92
     الحالي
    -1.92
    st
    -1.87
     jenem
    -1.87
    POSITIVE LOGITS
    sudadera
    2.23
    瑧
    2.17
     informar
    2.06
    玢
    2.03
    灃
    1.98
    isierte
    1.93
    谞
    1.88
    ݯ
    1.84
     esses
    1.84
    ﹶ
    1.82
    Activations Density 0.002%

    No Known Activations