© 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. 9219
    Prev
    Next
    INDEX
    Explanations

    pronouns and modal verbs followed by context

    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
    够了
    -1.45
    
    -1.45
    Ꮺ
    -1.44
    </u>
    -1.41
    🧌
    -1.40
     tatuajes
    -1.40
    헷
    -1.39
    mga
    -1.38
    kopi
    -1.38
    tacos
    -1.38
    POSITIVE LOGITS
     if
    1.69
    vyšší
    1.44
    了个
    1.38
    sheet
    1.36
     to
    1.35
    send
    1.33
    genicity
    1.30
     for
    1.30
    ницей
    1.27
     
    1.27
    Activations Density 0.091%

    No Known Activations