© 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. 267
    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
     encompasses
    -1.06
     blivit
    -0.97
    MMV
    -0.94
     tailored
    -0.90
    VERTICAL
    -0.88
    Tudo
    -0.88
    Ethnicity
    -0.85
     ország
    -0.85
    vestido
    -0.84
    加速
    -0.84
    POSITIVE LOGITS
    ÍS
    1.05
     to
    1.02
    擤
    0.99
    iding
    0.92
    כון
    0.91
    ológica
    0.90
     and
    0.89
    ise
    0.87
     детские
    0.87
    ka
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.