© 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. 13265
    Prev
    Next
    INDEX
    Explanations

    end punctuation or clause separators

    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
    举动
    -1.05
    breviation
    -0.96
    rdoba
    -0.96
    ほうがいい
    -0.95
     clés
    -0.95
     secundarios
    -0.92
    ècle
    -0.92
     میکنه
    -0.90
     >
    -0.88
     sorpresas
    -0.88
    POSITIVE LOGITS
     définiti
    1.15
     erreichbar
    1.00
     médicaux
    0.95
     siècles
    0.91
    си
    0.87
     is
    0.87
     Græ
    0.87
    ками
    0.86
     anvä
    0.85
    UDC
    0.84
    Activations Density 0.094%

    No Known Activations