© 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. 22-GEMMASCOPE-RES-131K
    7. 39964
    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
    çoivent
    -1.13
     (
    -0.99
    と呼ばれる
    -0.98
    fiets
    -0.96
     éves
    -0.95
    kanı
    -0.93
     canina
    -0.92
     (“
    -0.90
     izle
    -0.90
    имущества
    -0.88
    POSITIVE LOGITS
    了下
    1.02
     (!__
    0.93
    pragma
    0.90
     he
    0.90
    本章
    0.89
    大人気
    0.88
    για
    0.85
    >
    0.84
    Med
    0.83
    escrit
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.