© 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. 10-GEMMASCOPE-RES-131K
    7. 10784
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bbero
    -1.31
    ri
    -1.24
     fester
    -1.20
    戗
    -1.20
    ”
    -1.20
     wmns
    -1.18
     bant
    -1.16
     này
    -1.16
    Люди
    -1.14
    里的
    -1.13
    POSITIVE LOGITS
     to
    1.36
     its
    1.30
    讫
    1.27
    。】
    1.27
     if
    1.23
    と呼ば
    1.22
     acompañ
    1.20
    鐧
    1.20
     aliviar
    1.20
     {
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.