© 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. 21492
    Prev
    Next
    INDEX
    Explanations

    after all

    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
     of
    -1.77
     επίσης
    -1.62
     البته
    -1.61
     again
    -1.59
    Inggris
    -1.34
    ࿚
    -1.32
     मेरे
    -1.24
     as
    -1.23
     inapropiados
    -1.23
     mismas
    -1.22
    POSITIVE LOGITS
    °;
    1.48
    intos
    1.40
    “:
    1.38
    »:
    1.38
     ſta
    1.37
    「
    1.36
    »;
    1.32
    '';
    1.32
    %?
    1.31
    °/
    1.31
    Activations Density 0.011%

    No Known Activations