© 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. 11170
    Prev
    Next
    INDEX
    Explanations

    domain names and structured data identifiers

    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
     of
    -1.52
     an
    -1.24
     from
    -1.22
     before
    -1.20
     for
    -1.20
     vuitton
    -1.20
    Dijo
    -1.17
    HANGUL
    -1.13
     alam
    -1.12
     revital
    -1.12
    POSITIVE LOGITS
     fiabilidad
    1.46
    這麼
    1.35
    こんなに
    1.32
    当即
    1.31
     decidedly
    1.30
     ridiculously
    1.28
    そんなに
    1.27
     startling
    1.27
     meravigli
    1.27
     amazingly
    1.24
    Activations Density 0.003%

    No Known Activations