© 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. 19201
    Prev
    Next
    INDEX
    Explanations

    parentheses for grouping

    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
    愎
    -3.92
    ーズン
    -3.19
    ſſen
    -3.19
     parut
    -3.02
    swire
    -2.92
    䛗
    -2.91
    茕
    -2.89
    诳
    -2.84
    圌
    -2.81
    ྒྱ
    -2.75
    POSITIVE LOGITS
    ’
    4.22
    /
    3.39
    _
    2.94
    –
    2.89
    )
    2.69
    ("
    2.48
     
    2.42
    2.42
    {
    2.38
    ":
    2.36
    Activations Density 0.002%

    No Known Activations