© 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. 84997
    Prev
    Next
    INDEX
    Explanations

    word of

    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
    ubernur
    -1.50
     and
    -1.47
     consentimento
    -1.40
     unſ
    -1.38
     činnosti
    -1.36
    "))
    -1.35
     for
    -1.33
    TResult
    -1.32
     одежда
    -1.30
     agrav
    -1.30
    POSITIVE LOGITS
    評價
    1.43
    2
    1.34
    噼
    1.31
     emporter
    1.30
    Продам
    1.29
    3
    1.29
     could
    1.26
    圖片
    1.25
    但也
    1.22
    jardins
    1.22
    Activations Density 0.139%

    No Known Activations