© 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. 22-GEMMASCOPE-RES-131K
    7. 75149
    Prev
    Next
    INDEX
    Explanations

    programming keywords or variables

    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_22/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
     and
    -1.23
    Inggris
    -1.10
    djang
    -1.09
    Gambar
    -1.03
    slika
    -1.02
    scrapy
    -1.02
    sommer
    -1.01
    Komentar
    -1.01
    hashtag
    -0.97
     čaj
    -0.96
    POSITIVE LOGITS
    assert
    1.05
    m
    0.96
    H
    0.94
    T
    0.94
    F
    0.91
    V
    0.91
    G
    0.89
     if
    0.88
    if
    0.88
    <em>
    0.88
    Activations Density 0.014%

    No Known Activations