© 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. 34-GEMMASCOPE-RES-131K
    4. 87035
    Prev
    Next
    INDEX
    Explanations

    person titles followed by names

    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_34/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
    kuun
    -0.97
     F
    -0.95
     Lucille
    -0.94
    Composição
    -0.92
     inventors
    -0.91
    Conteúdo
    -0.91
    =?,
    -0.88
    ViewChild
    -0.88
     Pastikan
    -0.88
     l
    -0.87
    POSITIVE LOGITS
     auffi
    1.23
    鋮
    1.14
    ïque
    1.13
     aprendizagem
    1.13
     ainfi
    1.13
    Todd
    1.08
     zkou
    1.05
     băr
    1.04
     revered
    1.03
     garantia
    1.03
    Activations Density 0.174%

    No Known Activations