© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42551
    Prev
    Next
    INDEX
    Explanations

    percentages and rates

    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
     pegatinas
    -1.55
     sillas
    -1.51
    hassee
    -1.47
     vacunas
    -1.46
    agus
    -1.41
     OGSÅ
    -1.40
    InstrumentedTest
    -1.37
     folosit
    -1.36
    casian
    -1.34
     lámparas
    -1.31
    POSITIVE LOGITS
     in
    2.53
     of
    2.09
     after
    1.66
     at
    1.59
     for
    1.52
     $
    1.35
     For
    1.34
      
    1.33
     on
    1.31
     .
    1.31
    Activations Density 0.036%

    No Known Activations