© 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. 34-GEMMASCOPE-RES-131K
    7. 106371
    Prev
    Next
    INDEX
    Explanations

    github links and scripts

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    jeb
    -0.77
     Reactivity
    -0.73
    SHE
    -0.69
    年間
    -0.66
    pli
    -0.65
     plaster
    -0.63
    Ple
    -0.62
     reactivity
    -0.62
     phospho
    -0.62
     asynchronously
    -0.61
    POSITIVE LOGITS
     aient
    0.66
     zda
    0.63
    WebElementEntity
    0.63
     рады
    0.62
     hned
    0.62
     hauteur
    0.62
    hideLoading
    0.61
    ũ
    0.61
    segunda
    0.61
     đây
    0.60
    Activations Density 0.067%

    No Known Activations