© 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. 22-GEMMASCOPE-RES-131K
    7. 28520
    Prev
    Next
    INDEX
    Explanations

    biography, referred, Gale, Patrick

    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_22/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
    dirond
    -1.04
    postolic
    -1.02
    𓂂
    -0.98
    ()?
    -0.96
     partir
    -0.96
     بیماری
    -0.95
     klap
    -0.94
    ::::::::::::::::
    -0.94
    зать
    -0.94
     ··
    -0.93
    POSITIVE LOGITS
     biraz
    1.13
    с
    1.09
     reikia
    1.05
     некото
    1.05
    把我
    1.04
    [\
    1.03
     Rasen
    1.03
     îi
    1.02
    Rise
    1.02
     sviluppo
    1.01
    Activations Density 0.038%

    No Known Activations