© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67956
    Prev
    Next
    INDEX
    Explanations

    Hot tips

    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
    そこに
    -0.88
     Чтобы
    -0.86
    following
    -0.86
     Whereas
    -0.84
    gucigalpa
    -0.83
     simile
    -0.82
     encontrada
    -0.81
     atualmente
    -0.80
    glob
    -0.80
     Этот
    -0.79
    POSITIVE LOGITS
     and
    1.03
    кости
    0.91
    teeth
    0.84
    boyfriend
    0.83
    bluza
    0.81
     plumas
    0.80
     straff
    0.79
     руку
    0.78
     mixte
    0.77
    /***
    
    0.77
    Activations Density 0.001%

    No Known Activations