© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    in that case scenarios

    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
     dochter
    -1.57
     desafios
    -1.53
    INCLUD
    -1.51
    cortina
    -1.48
     desafio
    -1.46
     of
    -1.46
    émoc
    -1.45
    escudo
    -1.44
     şeyi
    -1.44
     eleições
    -1.42
    POSITIVE LOGITS
     if
    1.95
     you
    1.88
    If
    1.82
    {
    1.78
     be
    1.72
    S
    1.71
     then
    1.69
    3
    1.59
     more
    1.58
     want
    1.57
    Activations Density 0.017%

    No Known Activations