© 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. 10-GEMMASCOPE-RES-131K
    7. 123680
    Prev
    Next
    INDEX
    Explanations

    Magna Carta, Magna Cum Laude, Habitat for Humanity

    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_10/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
    ."
    -2.27
    各样的
    -2.05
     його
    -1.98
     estos
    -1.96
    盌
    -1.95
    readFileSync
    -1.93
    ".
    -1.88
     -
    -1.88
     の
    -1.86
    0
    -1.84
    POSITIVE LOGITS
     ܙ
    2.25
    趼
    2.19
    ↵
    2.17
    ﺢ
    2.16
     ferv
    2.16
     japonesa
    2.11
    踯
    2.11
    茕
    2.06
     grigio
    2.05
     vendido
    2.05
    Activations Density 0.002%

    No Known Activations