© 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. 34-GEMMASCOPE-RES-131K
    7. 79090
    Prev
    Next
    INDEX
    Explanations

    class and interface definitions

    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_34/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
     meis
    -0.88
    Municipio
    -0.86
     kev
    -0.86
    ỳnh
    -0.85
     dames
    -0.85
     LEGEND
    -0.84
     ruines
    -0.84
     Korn
    -0.84
     UIN
    -0.83
     DICTION
    -0.82
    POSITIVE LOGITS
     Point
    1.23
     person
    1.22
     Person
    1.14
     Human
    1.13
    Point
    1.13
     my
    1.13
     rectangle
    1.12
     Student
    1.12
     Animal
    1.09
     Employee
    1.09
    Activations Density 0.152%

    No Known Activations