© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35247
    Prev
    Next
    INDEX
    Explanations

    specific word formations

    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
    انگ
    -1.03
     ایر
    -1.00
     Ră
    -0.98
     conster
    -0.96
     multicolore
    -0.96
     galeria
    -0.94
    菒
    -0.93
     queste
    -0.91
     إسرائيل
    -0.91
    라는
    -0.91
    POSITIVE LOGITS
    Since
    1.05
     більш
    1.02
    mudah
    1.01
    During
    1.00
    Приятного
    0.98
    🎵
    0.97
    Rozmiar
    0.96
    具体的な
    0.96
     willkommen
    0.96
     інші
    0.96
    Activations Density 0.052%

    No Known Activations