© 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. 104945
    Prev
    Next
    INDEX
    Explanations

    sentence connectors after punctuation

    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
     OGSÅ
    -1.80
    
    -1.78
    賒
    -1.69
    玘
    -1.66
    Diese
    -1.63
    Previously
    -1.63
    Эти
    -1.63
    bebasan
    -1.61
     schnell
    -1.59
     Kulit
    -1.59
    POSITIVE LOGITS
    </strong>
    2.19
     hängt
    1.98
    ль
    1.90
     cuentan
    1.83
     It
    1.82
     verás
    1.67
    」(
    1.65
    ных
    1.63
     disfru
    1.63
    ти
    1.59
    Activations Density 0.085%

    No Known Activations