© 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. 34-GEMMASCOPE-RES-131K
    7. 116805
    Prev
    Next
    INDEX
    Explanations

    Chinese and Korean names

    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_34/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
    煕
    -0.78
    ності
    -0.77
     λ
    -0.73
    聡
    -0.72
    دع
    -0.72
    sedown
    -0.71
    aves
    -0.71
    abilidade
    -0.71
    ("^
    -0.70
     Damascus
    -0.69
    POSITIVE LOGITS
     assorted
    0.87
    ochim
    0.81
     경
    0.81
     erfahren
    0.81
     eleg
    0.80
     lata
    0.80
     略
    0.79
    <blockquote>
    0.79
    芯片
    0.78
    由
    0.78
    Activations Density 0.009%

    No Known Activations