© 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. 1220
    Prev
    Next
    INDEX
    Explanations

    flags and banners

    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
     In
    -2.00
     verhindern
    -1.73
    Also
    -1.57
     нее
    -1.52
    也可
    -1.49
     भी
    -1.49
     but
    -1.49
    WRENCE
    -1.43
    In
    -1.41
    ítima
    -1.41
    POSITIVE LOGITS
    旆
    1.88
    醅
    1.72
    隳
    1.66
     banners
    1.64
     Strukt
    1.64
    皤
    1.61
     sosi
    1.59
    岜
    1.58
     flags
    1.57
     mostrare
    1.54
    Activations Density 0.021%

    No Known Activations