© 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. 32894
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases

    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
    eight
    -1.26
     regalías
    -1.13
     dilapidated
    -1.10
     втором
    -1.09
     enthält
    -1.09
     einschließlich
    -1.08
    seven
    -1.08
    </i>
    -1.07
     применя
    -1.07
    celand
    -1.06
    POSITIVE LOGITS
     that
    2.48
     osal
    1.36
     whose
    1.34
    　　【
    1.34
     burbu
    1.33
     problemi
    1.30
     for
    1.30
    ÁT
    1.29
     rios
    1.29
    مقدمه
    1.27
    Activations Density 0.155%

    No Known Activations