© 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. 10974
    Prev
    Next
    INDEX
    Explanations

    mystery

    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
    廰
    -2.55
    平时
    -2.34
    луйста
    -2.23
     entirety
    -2.22
     proposées
    -2.17
    ſten
    -2.13
    迄
    -2.08
    ">
    -2.05
     distur
    -2.03
    یزات
    -2.02
    POSITIVE LOGITS
    .
    2.73
    ↵
    2.73
    夸张
    2.31
    璆
    2.31
     blanca
    2.31
    瑧
    2.25
    将她
    2.19
    鑄
    2.19
    vantaged
    2.14
    滬
    2.14
    Activations Density 0.004%

    No Known Activations