© 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. 10-GEMMASCOPE-RES-131K
    7. 19198
    Prev
    Next
    INDEX
    Explanations

    slum, ghetto, grassland, corrosion, glossary

    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_10/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
    獴
    -2.92
    魨
    -2.83
    ーズン
    -2.70
    
    -2.67
    ごめんなさい
    -2.64
    谂
    -2.63
    慙
    -2.55
    ஂ
    -2.52
    ༑
    -2.47
    錞
    -2.47
    POSITIVE LOGITS
     of
    3.22
    "
    3.16
    ’
    2.88
    s
    2.64
    (
    2.64
    ."
    2.44
     '
    2.41
     for
    2.34
    ↵↵
    2.28
    )
    2.08
    Activations Density 0.004%

    No Known Activations