© 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. 102208
    Prev
    Next
    INDEX
    Explanations

    names following parts of other names

    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
     especially
    -1.69
     then
    -1.63
     as
    -1.56
     like
    -1.55
     and
    -1.52
     a
    -1.51
     so
    -1.49
     more
    -1.48
     all
    -1.48
     since
    -1.47
    POSITIVE LOGITS
    2
    1.78
    ícias
    1.66
    6
    1.54
     этих
    1.50
    4
    1.48
    9
    1.45
     упаков
    1.45
     peuvent
    1.42
     вашу
    1.36
    が無い
    1.34
    Activations Density 0.181%

    No Known Activations