© 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. 112725
    Prev
    Next
    INDEX
    Explanations

    understand questions or confusion

    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
    よりも
    -1.45
    probably
    -1.43
     orilla
    -1.31
    不好意思
    -1.25
     hason
    -1.22
     demostrado
    -1.21
     connues
    -1.20
     probablement
    -1.20
     can
    -1.19
     élevés
    -1.19
    POSITIVE LOGITS
     but
    1.79
     which
    1.77
     why
    1.63
     or
    1.51
     waarom
    1.44
     new
    1.35
     using
    1.32
     memenuhi
    1.32
    TProtocol
    1.31
     if
    1.28
    Activations Density 0.102%

    No Known Activations