© 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. 104642
    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
     exquisitely
    -1.43
    Высота
    -1.42
    いよいよ
    -1.40
    定価
    -1.39
    ⸒
    -1.38
    Каждый
    -1.36
    Tú
    -1.35
    Фак
    -1.33
    Они
    -1.29
     obsessive
    -1.28
    POSITIVE LOGITS
    _
    1.56
     REALLY
    1.49
    '
    1.42
    
    1.38
    despite
    1.36
     remarkably
    1.34
     somewhat
    1.34
     fortement
    1.34
     betreffende
    1.34
    usually
    1.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.