© 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. 48386
    Prev
    Next
    INDEX
    Explanations

    describing a state or characteristic

    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
    na
    -1.52
    o
    -1.50
    ka
    -1.48
    k
    -1.46
    get
    -1.41
    敉
    -1.36
    ียม
    -1.34
    ziplin
    -1.33
    i
    -1.33
     mediante
    -1.32
    POSITIVE LOGITS
     by
    1.74
     even
    1.53
    katalog
    1.45
     zelfs
    1.38
    produk
    1.34
     même
    1.33
     münchen
    1.32
    adalah
    1.32
    recen
    1.31
    kond
    1.30
    Activations Density 0.054%

    No Known Activations