© 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. 22-GEMMASCOPE-RES-131K
    7. 67445
    Prev
    Next
    INDEX
    Explanations

    baseball pitching terms

    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_22/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
     their
    -1.26
     kecelakaan
    -1.16
     chrétiens
    -1.13
    数百
    -1.07
     manzanas
    -1.03
     autobús
    -0.99
    énus
    -0.98
     tío
    -0.97
    ۔
    -0.95
    Depois
    -0.94
    POSITIVE LOGITS
     máme
    1.20
     spôso
    1.16
     zugänglich
    1.13
    氿
    1.13
     zuständig
    1.11
     řed
    1.10
     gyvento
    1.09
     nám
    1.09
     článku
    1.08
     tilgjenge
    1.08
    Activations Density 0.021%

    No Known Activations