© 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. 60521
    Prev
    Next
    INDEX
    Explanations

    examples with details

    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
     söyledi
    -1.45
     it
    -1.34
     可以
    -1.30
     kämp
    -1.23
    inição
    -1.21
     设置
    -1.21
     можно
    -1.21
    邂
    -1.18
     can
    -1.16
    橈
    -1.16
    POSITIVE LOGITS
    Ещё
    1.54
    Mengapa
    1.39
    多く
    1.38
     sebag
    1.38
    when
    1.36
    Еще
    1.34
    Karakteristik
    1.34
     even
    1.33
    Mesmo
    1.30
     ABBRE
    1.27
    Activations Density 0.006%

    No Known Activations