© 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. 22-GEMMASCOPE-RES-131K
    7. 129632
    Prev
    Next
    INDEX
    Explanations

    GIS mapping layers and vector data

    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_22/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
    谥
    -1.37
     Uniwersyte
    -1.33
     Instyt
    -1.30
    Quantidade
    -1.29
    []{"
    -1.27
     portátiles
    -1.27
    山上
    -1.23
    endmodule
    -1.23
    lossians
    -1.22
    OrNil
    -1.22
    POSITIVE LOGITS
    ﻷ
    1.91
    ﻻ
    1.61
    ﷲ
    1.39
     vielfäl
    1.36
    ﻹ
    1.33
     iniziale
    1.30
    områ
    1.27
     pubblico
    1.27
     they
    1.26
     unangemess
    1.26
    Activations Density 0.037%

    No Known Activations