© 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. 103292
    Prev
    Next
    INDEX
    Explanations

    followed by proper nouns

    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
    カテゴリ
    -0.94
     尼
    -0.81
     методом
    -0.78
     יִ
    -0.78
     qualche
    -0.77
    əri
    -0.76
     мора
    -0.76
    下方
    -0.75
     매우
    -0.74
     tež
    -0.74
    POSITIVE LOGITS
    らく
    1.30
     Mayhem
    1.08
    packs
    1.01
     MUM
    0.99
     UM
    0.97
    Whereas
    0.95
    whereas
    0.95
    🖼
    0.94
     Mustangs
    0.94
    カテ
    0.91
    Activations Density 2.287%

    No Known Activations