© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47748
    Prev
    Next
    INDEX
    Explanations

    try to, make, provide, update

    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
     for
    -1.62
     outros
    -1.55
     otras
    -1.41
     one
    -1.39
    gafas
    -1.34
     altre
    -1.33
     शुर
    -1.32
     two
    -1.30
     diğer
    -1.30
     outras
    -1.27
    POSITIVE LOGITS
     alemanes
    1.37
    也能
    1.28
     ſmall
    1.20
     نداشته
    1.17
    ኽ
    1.17
     Exteriores
    1.16
     نشده
    1.16
    丄
    1.15
     acordo
    1.15
     olika
    1.12
    Activations Density 0.044%

    No Known Activations