© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39911
    Prev
    Next
    INDEX
    Explanations

    months of dates

    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
     this
    -1.45
    Напомним
    -1.13
     gir
    -1.11
    उत्तर
    -1.09
    
    -1.04
    यह
    -1.02
     abril
    -1.00
     diferentes
    -0.99
     how
    -0.98
    nextProps
    -0.98
    POSITIVE LOGITS
     onları
    0.95
    prong
    0.95
     prêtres
    0.92
    enseignement
    0.91
    ve
    0.90
     رغم
    0.89
     mittler
    0.88
    distribute
    0.88
     Their
    0.86
     alltid
    0.86
    Activations Density 0.025%

    No Known Activations