© 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. 9170
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     good
    -1.66
    \
    -1.62
     p
    -1.62
     so
    -1.59
     well
    -1.59
     this
    -1.55
     to
    -1.45
     only
    -1.45
     three
    -1.41
     other
    -1.41
    POSITIVE LOGITS
     solidar
    1.69
     robuste
    1.54
     unſ
    1.53
     vernac
    1.52
     munt
    1.52
     autonomie
    1.52
     ſever
    1.51
     menik
    1.51
     applau
    1.50
     incess
    1.49
    Activations Density 0.028%

    No Known Activations