© 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. 10-GEMMASCOPE-RES-131K
    7. 3894
    Prev
    Next
    INDEX
    Explanations

    Chinese place names

    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_10/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
    二日
    -2.02
     "
    -1.93
    </i>
    -1.88
     edisi
    -1.82
    Caratteristiche
    -1.80
     When
    -1.77
     OGSÅ
    -1.77
     or
    -1.76
     Resmi
    -1.70
    e
    -1.70
    POSITIVE LOGITS
    
    2.08
    歺
    2.00
    ensdag
    1.89
    这也
    1.85
    ඍ
    1.80
     same
    1.80
     pfle
    1.80
    ⏑
    1.77
    ………
    1.77
    ৢ
    1.77
    Activations Density 0.014%

    No Known Activations