© 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. 70305
    Prev
    Next
    INDEX
    Explanations

    connecting clauses

    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
     typelib
    -1.71
     or
    -1.66
     to
    -1.61
     that
    -1.48
     each
    -1.46
    gulation
    -1.39
     those
    -1.37
    жела
    -1.36
     упаковки
    -1.36
    gées
    -1.35
    POSITIVE LOGITS
     inférieur
    1.76
     этого
    1.59
     ferrovi
    1.55
    幾天
    1.55
    Its
    1.44
    也不會
    1.42
     มัน
    1.41
     alguns
    1.40
    linien
    1.39
    都沒
    1.39
    Activations Density 0.107%

    No Known Activations