© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105000
    Prev
    Next
    INDEX
    Explanations

    asking, saying, telling

    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
     then
    -1.75
    zelfde
    -1.63
     by
    -1.62
     always
    -1.52
     there
    -1.51
     on
    -1.46
     will
    -1.39
     Económica
    -1.35
     have
    -1.35
     subsequent
    -1.34
    POSITIVE LOGITS
     =
    1.22
     können
    1.21
    囁
    1.21
     podmín
    1.21
     prénom
    1.20
     gezin
    1.17
    5
    1.16
     problèmes
    1.16
     soucis
    1.16
    ктей
    1.13
    Activations Density 0.027%

    No Known Activations