© 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. 103967
    Prev
    Next
    INDEX
    Explanations

    single noun

    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
     แต่
    -1.92
    ar
    -1.91
    でも
    -1.89
     trám
    -1.73
     achet
    -1.71
     marqués
    -1.71
    y
    -1.67
    zetek
    -1.64
     But
    -1.64
     sprüche
    -1.63
    POSITIVE LOGITS
    ischof
    1.88
    приятие
    1.83
    vantaged
    1.82
    あります
    1.81
    ﾆ
    1.80
    ている
    1.77
    欅
    1.77
    飚
    1.76
    それとも
    1.76
    ﾏ
    1.74
    Activations Density 0.006%

    No Known Activations