© 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. 27915
    Prev
    Next
    INDEX
    Explanations

    xml, diagnostic, electrocardiogram, arylsulfatase

    np_acts-logits-general · gemini-2.5-flash-lite

    programming language syntax related to namespaces, system libraries, and code annotations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     another
    -1.23
     last
    -1.05
     it
    -1.05
     through
    -1.02
    kı
    -1.01
     have
    -0.98
     Tenggara
    -0.98
    が
    -0.97
     its
    -0.97
     Milán
    -0.96
    POSITIVE LOGITS
    u
    1.07
    leyball
    1.05
     dessas
    0.98
     específicamente
    0.98
     gefährlich
    0.97
     الأع
    0.95
     Eventually
    0.95
     ilyen
    0.94
    whenever
    0.94
     fx
    0.93
    Activations Density 0.002%

    No Known Activations