© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11946
    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
     which
    -1.02
     likely
    -0.94
     innych
    -0.92
     terwijl
    -0.91
     other
    -0.91
     matrícula
    -0.90
     claust
    -0.90
     unless
    -0.90
    vados
    -0.86
     "..\..\
    -0.85
    POSITIVE LOGITS
     ortam
    1.26
     obedience
    1.01
    短い
    0.97
     pajak
    0.96
     operativo
    0.93
     impromptu
    0.92
     refresher
    0.88
     propias
    0.88
     instinctive
    0.88
    チコミ
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.