© 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. 34-GEMMASCOPE-RES-131K
    4. 103327
    Prev
    Next
    INDEX
    Explanations

    latex fractions containing mathematical symbols

    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_34/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
     their
    -1.13
    进入了
    -0.95
    With
    -0.95
     such
    -0.94
    For
    -0.94
    Three
    -0.93
     deschis
    -0.93
    Four
    -0.92
    Those
    -0.92
    nipeg
    -0.91
    POSITIVE LOGITS
    frac
    2.95
    mfrac
    2.48
     “
    1.90
     "
    1.71
     how
    1.52
     frac
    1.48
     „
    1.23
    「
    1.20
     way
    1.17
     the
    1.14
    Activations Density 0.015%

    No Known Activations