© 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. 48538
    Prev
    Next
    INDEX
    Explanations

    acts as comparison or classification

    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
     the
    -2.14
    -
    -1.97
     is
    -1.84
     or
    -1.73
    偲
    -1.72
    ()}>
    -1.63
    瞑
    -1.59
     an
    -1.56
    it
    -1.48
     that
    -1.48
    POSITIVE LOGITS
     obicei
    2.16
     solicitudes
    2.09
     моего
    2.09
     нашего
    2.08
     vacunas
    2.03
     naszego
    1.94
     deudas
    1.94
     naszej
    1.92
     нашем
    1.92
    őben
    1.90
    Activations Density 0.243%

    No Known Activations