© 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. 95779
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and letters

    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
     ahí
    -0.84
     Editing
    -0.84
    ということです
    -0.83
     исте
    -0.82
     tenga
    -0.82
    visiting
    -0.82
     hatten
    -0.82
     presidenta
    -0.81
    там
    -0.79
     estamp
    -0.79
    POSITIVE LOGITS
    ができます
    1.14
     miraculously
    1.06
     fiercely
    1.05
     sorely
    1.02
     Chara
    1.02
     adversely
    0.98
     fiabilidad
    0.96
    MergeFrom
    0.96
     Influenza
    0.95
    遗址
    0.94
    Activations Density 0.148%

    No Known Activations