© 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. 79842
    Prev
    Next
    INDEX
    Explanations

    calendar dates

    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
    óság
    -0.88
     內
    -0.86
    꾀
    -0.86
     estadía
    -0.86
     bakso
    -0.86
     Désolé
    -0.86
     perguntou
    -0.85
    zések
    -0.85
     gomez
    -0.85
    ඌ
    -0.84
    POSITIVE LOGITS
    不受
    0.99
     buf
    0.89
     câu
    0.85
    
    0.84
     meurt
    0.82
     growing
    0.81
     inaprop
    0.81
    valido
    0.80
    broker
    0.79
    ktiv
    0.79
    Activations Density 0.000%

    No Known Activations