© 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. 9207
    Prev
    Next
    INDEX
    Explanations

    fundraising events and specific entities

    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
     It
    -2.83
    是
    -2.53
    我很
    -2.45
    大腿
    -2.44
    不會
    -2.41
    不錯
    -2.36
    关键
    -2.30
    Ꮬ
    -2.30
    genodigd
    -2.30
    他
    -2.28
    POSITIVE LOGITS
    龊
    2.92
    a
    2.88
    沨
    2.83
     parachoque
    2.55
    ”
    2.53
    .
    2.50
    鋮
    2.48
    姈
    2.41
    ᯾
    2.39
     تعدى
    2.25
    Activations Density 0.001%

    No Known Activations