© 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. 119774
    Prev
    Next
    INDEX
    Explanations

    how much questions

    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
    大家都
    -2.19
    小弟
    -2.00
    正如
    -1.93
    媄
    -1.89
    韓國
    -1.88
    近年
    -1.79
     aprobó
    -1.77
    楊
    -1.75
     materiál
    -1.74
    狆
    -1.74
    POSITIVE LOGITS
    ⩴
    2.02
    沨
    2.00
    $
    1.82
     they
    1.79
    which
    1.77
    檍
    1.75
     Voit
    1.73
    ビックリ
    1.72
    饪
    1.71
     you
    1.70
    Activations Density 0.003%

    No Known Activations