© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68518
    Prev
    Next
    INDEX
    Explanations

    theta state

    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
    Negative Logits
     was
    -2.47
    uró
    -2.02
     From
    -2.02
    észetes
    -2.02
     Aufen
    -2.00
    atação
    -1.96
     insists
    -1.93
    s
    -1.93
     після
    -1.90
    ivotopis
    -1.90
    POSITIVE LOGITS
    .
    2.80
    2.66
    {
    2.03
    ir
    1.80
     ハ
    1.77
     innymi
    1.77
     destacan
    1.75
     a
    1.75
    O
    1.74
     presque
    1.73
    Activations Density 0.006%
    No Known Activations