© 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. 27755
    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
    queiro
    -1.13
     from
    -1.09
     has
    -1.04
     like
    -1.02
     have
    -0.96
     you
    -0.94
     by
    -0.94
     Tenggara
    -0.90
    とこ
    -0.90
     to
    -0.90
    POSITIVE LOGITS
     spesielt
    1.10
    Ὕ
    1.02
    かを
    1.02
    λίου
    1.01
     fusca
    1.00
    எ
    1.00
    tiy
    0.98
    (>
    0.98
     комплекте
    0.98
     exemplu
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.