© 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. 42036
    Prev
    Next
    INDEX
    Explanations

    technical terms, acronyms, and domain names

    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
    cepatan
    -1.40
     другими
    -1.39
     preescolar
    -1.38
    Tecnologia
    -1.38
    IBLES
    -1.35
     других
    -1.30
    other
    -1.30
     fortsatt
    -1.30
     掛け
    -1.30
    บ้าง
    -1.29
    POSITIVE LOGITS
    u
    1.58
    ()]);
    1.46
    ceous
    1.34
     Access
    1.34
     about
    1.34
    ę
    1.31
    ).
    1.26
    可以说
    1.25
    比べると
    1.23
    The
    1.22
    Activations Density 0.019%

    No Known Activations