© 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. 28018
    Prev
    Next
    INDEX
    Explanations

    buy or purchase something

    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
     its
    -1.13
    各项
    -1.12
    unción
    -1.12
     которое
    -1.11
    因为它
    -1.09
    财富
    -1.08
     when
    -1.05
    前は
    -1.05
     because
    -1.05
     flotante
    -1.05
    POSITIVE LOGITS
     a
    2.23
     new
    1.40
    new
    1.33
     nuovi
    1.30
     terminée
    1.27
     pauvre
    1.27
     nové
    1.22
    一个
    1.22
     kaksi
    1.20
     nuevos
    1.16
    Activations Density 0.025%

    No Known Activations