© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48777
    Prev
    Next
    INDEX
    Explanations

    numbered articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    種類
    -0.98
    četně
    -0.88
     fieltro
    -0.84
     maceta
    -0.83
    本書
    -0.82
    cích
    -0.82
     gelingt
    -0.81
    ˟
    -0.81
     ganchillo
    -0.80
    朝
    -0.79
    POSITIVE LOGITS
     Article
    1.93
     article
    1.69
    Article
    1.55
    article
    1.55
     Articles
    1.45
     Artikel
    1.39
     articles
    1.38
     ARTICLE
    1.34
     artículo
    1.27
     artikel
    1.24
    Activations Density 0.006%

    No Known Activations