© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1386
    Prev
    Next
    INDEX
    Explanations

    thoughts, views, perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ać
    3.36
    ﮄ
    2.75
    дить
    2.62
    मर्रा
    2.62
    ۝
    2.60
    aing
    2.57
    挕
    2.56
    瓄
    2.56
    ólico
    2.54
    
    2.54
    POSITIVE LOGITS
     '
    2.14
     Husk
    2.12
    চিন্ত
    2.03
     পোষণ
    1.98
     맞
    1.94
     ASP
    1.90
     larg
    1.88
    hip
    1.87
    1
    1.87
     passed
    1.86
    Activations Density 0.455%

    No Known Activations