© 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. 123878
    Prev
    Next
    INDEX
    Explanations

    low lying rural and useful information

    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
    希望
    -1.73
     The
    -1.66
    い
    -1.63
     只
    -1.55
    より
    -1.55
     необходимости
    -1.55
     zust
    -1.52
    目前
    -1.50
     обеспечения
    -1.50
    我在
    -1.48
    POSITIVE LOGITS
    ⑉
    1.84
    
    1.77
    𝘇
    1.73
    鋮
    1.69
    jší
    1.69
    ově
    1.68
     grève
    1.67
    esine
    1.63
     maupun
    1.63
    ,…
    1.62
    Activations Density 0.012%

    No Known Activations