© 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. 104563
    Prev
    Next
    INDEX
    Explanations

    titles and foreign phrases

    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
    のですね
    -1.19
    為に
    -1.11
     Использу
    -1.10
    这样做
    -1.04
    ことも
    -1.03
    感じで
    -1.03
    んですね
    -1.02
    はずです
    -1.00
     նաև
    -0.99
    方がいい
    -0.98
    POSITIVE LOGITS
     is
    1.08
    Lịch
    1.05
    Makanan
    1.04
    ousness
    1.03
     áreas
    1.01
    alties
    1.00
     lugar
    0.99
     mandato
    0.97
    Ofer
    0.96
    もあります
    0.96
    Activations Density 0.044%

    No Known Activations