© 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. 83900
    Prev
    Next
    INDEX
    Explanations

    ways followed by descriptions

    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
    THERE
    -1.36
     personen
    -1.20
    strukturen
    -1.18
     territoriale
    -1.14
    Décès
    -1.13
    palindrome
    -1.13
    एको
    -1.12
    龋
    -1.10
    Показать
    -1.09
    què
    -1.07
    POSITIVE LOGITS
     {
    1.66
     both
    1.64
     we
    1.54
     its
    1.54
     simply
    1.44
     [
    1.37
     it
    1.35
     now
    1.34
     you
    1.33
     poprzez
    1.30
    Activations Density 0.269%

    No Known Activations