© 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. 129923
    Prev
    Next
    INDEX
    Explanations

    Scala code

    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
    Ծանոթ
    -1.25
     this
    -1.20
     grat
    -1.19
     which
    -1.18
    збе
    -1.15
    瀦
    -1.14
    Considerations
    -1.14
     for
    -1.13
    CONTEN
    -1.13
    lossenen
    -1.12
    POSITIVE LOGITS
     какво
    1.38
     are
    1.31
     échelle
    1.30
     cajas
    1.30
     ее
    1.30
     neumáticos
    1.29
     certificados
    1.29
     how
    1.27
     éxito
    1.25
    мѣ
    1.25
    Activations Density 0.065%

    No Known Activations