© 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. 102491
    Prev
    Next
    INDEX
    Explanations

    mapping props to actions

    np_acts-logits-general · gemini-2.5-flash-lite

    TypeScript type annotations and interface definitions, particularly for Props and generic types.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     in
    -2.67
     it
    -1.65
     to
    -1.61
     by
    -1.49
     out
    -1.45
     a
    -1.41
     next
    -1.37
     other
    -1.34
     It
    -1.33
     although
    -1.32
    POSITIVE LOGITS
    Berikut
    1.44
    Semua
    1.32
     любую
    1.22
     použití
    1.22
     calzado
    1.21
     Irán
    1.21
     collectons
    1.20
    Banyak
    1.19
    滋賀
    1.18
    Includes
    1.17
    Activations Density 0.060%

    No Known Activations