© 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. 10-GEMMASCOPE-RES-131K
    7. 22733
    Prev
    Next
    INDEX
    Explanations

    four groups

    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
    Negative Logits
    あまり
    -1.58
    źdz
    -1.53
    ...");
    -1.52
    eventbus
    -1.38
    大量
    -1.38
    органи
    -1.37
     tampoco
    -1.36
    ため
    -1.34
     gdzie
    -1.34
     Tampoco
    -1.30
    POSITIVE LOGITS
    簡介
    1.67
    衚
    1.52
     venezolano
    1.45
    4
    1.45
     estatales
    1.44
    濵
    1.44
     різних
    1.41
    現貨
    1.39
    </h3>
    1.39
    萵
    1.38
    Activations Density 0.095%

    No Known Activations