© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    XML layout attributes

    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
     jezt
    -1.81
    🫴
    -1.72
    ==""){
    -1.72
     gouttes
    -1.66
     feria
    -1.65
    lxt
    -1.63
    🧌
    -1.60
    groet
    -1.57
    𐐀
    -1.56
    yyj
    -1.54
    POSITIVE LOGITS
     Those
    2.02
     as
    2.02
     still
    1.95
     Although
    1.84
     As
    1.74
     Still
    1.72
    на
    1.70
     участь
    1.70
     so
    1.68
    Those
    1.68
    Activations Density 0.002%

    No Known Activations