© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21112
    Prev
    Next
    INDEX
    Explanations

    UI elements and code snippets

    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
     for
    -1.86
     plethora
    -1.77
     in
    -1.75
    2
    -1.72
     on
    -1.71
     as
    -1.68
     with
    -1.65
     to
    -1.63
     has
    -1.63
     In
    -1.59
    POSITIVE LOGITS
     zwi
    1.81
    鲩
    1.81
     tunik
    1.76
     transak
    1.73
     Infór
    1.72
     kulinar
    1.71
     bluz
    1.70
     dezelve
    1.68
     vnnd
    1.67
     restes
    1.65
    Activations Density 0.027%

    No Known Activations