© 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. 253
    Prev
    Next
    INDEX
    Explanations

    lazy initialization

    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
    菹
    -3.78
     But
    -3.70
     แต่
    -3.38
    詎
    -2.98
    窳
    -2.97
    柺
    -2.94
    ݈
    -2.86
     nhưng
    -2.81
    鲵
    -2.81
    廰
    -2.73
    POSITIVE LOGITS
    0
    4.28
    b
    3.19
    get
    3.00
    8
    2.84
    s
    2.80
    y
    2.78
    6
    2.75
     gets
    2.66
    g
    2.63
    your
    2.58
    Activations Density 0.002%

    No Known Activations