© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14936
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     tunggu
    -1.45
    fangs
    -1.39
     ideen
    -1.37
     pikir
    -1.34
    рии
    -1.32
    ₋
    -1.30
    的で
    -1.30
     nomor
    -1.29
     their
    -1.29
    ˃
    -1.27
    POSITIVE LOGITS
     что
    1.38
     generalmente
    1.37
    虽说
    1.32
    "
    1.31
     unsere
    1.29
     assorted
    1.29
    がありますが
    1.28
     aún
    1.27
     ploy
    1.23
    1
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.