© 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. 35754
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    
    -0.86
    For
    -0.85
    Heidelberg
    -0.84
    ningens
    -0.82
     JsonConvert
    -0.81
    hmigung
    -0.80
     perils
    -0.78
     más
    -0.78
     For
    -0.78
    ++++
    -0.78
    POSITIVE LOGITS
     nörd
    0.95
    他們
    0.90
     enthou
    0.88
     salaire
    0.85
     rafraî
    0.84
    Szer
    0.84
     régal
    0.84
    ➬
    0.84
    兒子
    0.82
     entraî
    0.82
    Activations Density 0.054%

    No Known Activations