© 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. 11888
    Prev
    Next
    INDEX
    Explanations

    night and nocturnal

    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
    ୈ
    -2.05
     mentes
    -1.84
    羕
    -1.84
    geſ
    -1.69
    woners
    -1.68
     户
    -1.66
    髣
    -1.66
    medriver
    -1.65
     marinho
    -1.63
     έχουν
    -1.62
    POSITIVE LOGITS
    e
    2.25
    .
    2.00
     The
    1.94
     night
    1.80
    y
    1.67
     and
    1.61
     This
    1.59
     nite
    1.54
    凌晨
    1.53
     These
    1.51
    Activations Density 0.030%

    No Known Activations