© 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. 41407
    Prev
    Next
    INDEX
    Explanations

    one of the X

    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
     and
    -2.67
    และ
    -1.74
     themselves
    -1.73
     are
    -1.72
     bakom
    -1.58
     avulla
    -1.52
     liknande
    -1.48
    .";
    -1.47
    different
    -1.45
    ’:
    -1.45
    POSITIVE LOGITS
     if
    1.97
     that
    1.64
     any
    1.63
     then
    1.63
    том
    1.53
     laquelle
    1.51
    icioso
    1.49
     которое
    1.48
     is
    1.46
     calientes
    1.44
    Activations Density 0.075%

    No Known Activations