© 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. 94255
    Prev
    Next
    INDEX
    Explanations

    Chief titles

    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
     ordenar
    -0.87
     enamorado
    -0.84
     Besten
    -0.82
     مسئول
    -0.73
    coffret
    -0.72
    Enregistrer
    -0.71
    풍
    -0.71
    쁨
    -0.71
    boîte
    -0.71
     larmes
    -0.71
    POSITIVE LOGITS
     Justice
    0.91
     Electoral
    0.82
    javac
    0.74
    📉
    0.74
    Receiving
    0.73
    secret
    0.73
     Kardashian
    0.71
     PRO
    0.71
     convection
    0.71
     justices
    0.71
    Activations Density 0.024%

    No Known Activations