© 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. 19655
    Prev
    Next
    INDEX
    Explanations

    specific individual needs

    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
     armen
    -1.59
     soos
    -1.52
     twa
    -1.51
    seurs
    -1.50
     biet
    -1.41
     olie
    -1.40
    iets
    -1.38
     universite
    -1.37
    testen
    -1.36
     avon
    -1.36
    POSITIVE LOGITS
     how
    1.78
    をご覧ください
    1.49
     each
    1.45
    這裡
    1.43
     your
    1.41
     this
    1.39
     both
    1.39
    コチラ
    1.37
    どれだけ
    1.35
     prawidł
    1.31
    Activations Density 0.024%

    No Known Activations