© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25217
    Prev
    Next
    INDEX
    Explanations

    companies, customers, industry, shipping

    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
    titleMargin
    -1.25
    為に
    -1.23
     These
    -1.23
    gigabyte
    -1.16
    ఘ
    -1.15
    事です
    -1.13
    にならない
    -1.08
     Porém
    -1.06
     Unglück
    -1.05
    Ẩ
    -1.05
    POSITIVE LOGITS
    <bos>
    1.39
    ，
    1.35
    もちろん
    1.34
    そして
    1.23
     HAPPENED
    1.23
    、
    1.20
    や
    1.14
    <0xA3>
    1.12
     etc
    1.09
     SHOWS
    1.09
    Activations Density 0.026%

    No Known Activations