© 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. 99169
    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
    穑
    -1.32
    Thema
    -1.29
    
    -1.27
     グリル
    -1.21
     հղումներ
    -1.18
     yaprak
    -1.18
    豨
    -1.17
    izmus
    -1.17
    Polizei
    -1.16
    drei
    -1.14
    POSITIVE LOGITS
     is
    1.52
    ا
    1.30
    We
    1.27
    кова
    1.12
    ця
    1.09
     nuevos
    1.09
     وب
    1.09
    "
    1.05
     Даже
    1.05
     و
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.