© 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. 67990
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     helps
    -1.50
     allows
    -1.42
     helped
    -1.35
     Since
    -1.33
     team
    -1.33
     provides
    -1.32
     multifaceted
    -1.31
     prevents
    -1.30
     helping
    -1.30
     providing
    -1.27
    POSITIVE LOGITS
     kohta
    1.48
     втором
    1.45
    actually
    1.44
     is
    1.39
     timmar
    1.34
     noin
    1.34
    often
    1.32
    搅拌
    1.32
     liknande
    1.31
     напряжение
    1.30
    Activations Density 0.389%

    No Known Activations