© 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. 10146
    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
    یین
    -1.26
    会儿
    -1.23
    tling
    -1.22
    for
    -1.20
     each
    -1.19
    andı
    -1.15
    还没有
    -1.14
     niveaux
    -1.13
     successive
    -1.10
     other
    -1.09
    POSITIVE LOGITS
     mientras
    1.39
     também
    1.33
     как
    1.31
     Quando
    1.29
     estamos
    1.28
     Then
    1.27
     zarówno
    1.27
    худ
    1.26
     серый
    1.26
     también
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.