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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70604
    Prev
    Next
    INDEX
    Explanations

    layout attributes and IDs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     utveckling
    -1.71
    asties
    -1.70
    vlád
    -1.58
    がありますが
    -1.58
     möjlighet
    -1.55
     erfaren
    -1.53
    şağı
    -1.49
     första
    -1.49
     Sünde
    -1.48
     последние
    -1.45
    POSITIVE LOGITS
     this
    2.67
     of
    2.50
     for
    2.17
     such
    2.09
     who
    1.98
     that
    1.88
     your
    1.80
     each
    1.80
     these
    1.69
     which
    1.45
    Activations Density 0.049%

    No Known Activations