© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22161
    Prev
    Next
    INDEX
    Explanations

    math and scientific units

    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
     This
    -1.84
     What
    -1.78
     It
    -1.77
     misguided
    -1.74
    什麼
    -1.59
     There
    -1.55
     However
    -1.54
    It
    -1.44
     dubious
    -1.42
     staunch
    -1.40
    POSITIVE LOGITS
     them
    1.52
    则
    1.43
     the
    1.42
    𓆜
    1.35
     کسانی
    1.33
     ſtate
    1.33
    liegenden
    1.33
     skvě
    1.32
    Etc
    1.31
     増
    1.31
    Activations Density 0.017%

    No Known Activations