© 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. 10-GEMMASCOPE-RES-131K
    7. 74168
    Prev
    Next
    INDEX
    Explanations

    detecting questions

    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
     either
    -1.45
     jednou
    -1.42
     ederim
    -1.41
     terapé
    -1.35
    charest
    -1.29
     さん
    -1.23
    ftagPool
    -1.23
     เพราะ
    -1.22
    chmal
    -1.22
     between
    -1.22
    POSITIVE LOGITS
     the
    1.80
     it
    1.45
    來
    1.25
     teraz
    1.20
     巾
    1.20
    Tomorrow
    1.16
    Exciting
    1.15
    Congrats
    1.13
     কর
    1.13
    experienced
    1.12
    Activations Density 0.110%

    No Known Activations