© 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. 11866
    Prev
    Next
    INDEX
    Explanations

    place names prefixes and suffixes

    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
    ）、
    -1.48
     계획
    -1.45
    0
    -1.44
        
    -1.42
     giapponese
    -1.27
       
    -1.27
    ध्य
    -1.26
     बताया
    -1.24
     giàu
    -1.24
    ernsey
    -1.24
    POSITIVE LOGITS
    </h1>
    1.68
    䜣
    1.50
    肫
    1.46
    tivität
    1.45
     ומ
    1.41
     .
    1.38
    zation
    1.36
    钐
    1.36
    가
    1.35
    近づ
    1.34
    Activations Density 0.701%

    No Known Activations