© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103372
    Prev
    Next
    INDEX
    Explanations

    fool, foolhardy, April Fool's Day

    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
    鲣
    -2.30
    有着
    -2.28
    一般的
    -2.28
    ＂
    -2.22
    ㄎ
    -2.13
    なりません
    -2.11
    ～～～
    -2.09
    想要的
    -2.08
    久しぶり
    -2.08
     школы
    -2.08
    POSITIVE LOGITS
    }
    3.23
    谢谢你
    3.09
    我先
    2.94
    也
    2.81
    .
    2.52
    珰
    2.48
    玙
    2.45
    なども
    2.44
    来越
    2.41
    {
    2.34
    Activations Density 0.005%

    No Known Activations