© 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. 28500
    Prev
    Next
    INDEX
    Explanations

    endings and interjections

    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
     ``
    -0.96
     ”
    -0.93
     ''
    -0.90
    Ộ
    -0.87
    >`
    -0.87
    とろ
    -0.87
    為に
    -0.86
    JSONArray
    -0.86
    rrbracket
    -0.85
    ',
    
    -0.85
    POSITIVE LOGITS
    小伙伴
    1.19
     монтажа
    1.07
    бѣ
    1.00
     herido
    0.98
    ismer
    0.93
    Ꮏ
    0.91
     gondol
    0.89
     tạp
    0.89
    ⾒
    0.87
    IBIL
    0.86
    Activations Density 0.029%

    No Known Activations