© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73036
    Prev
    Next
    INDEX
    Explanations

    names, often preceded by "Dr."

    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
     другие
    -1.41
     пишет
    -1.39
    其他
    -1.35
    支持
    -1.31
     olika
    -1.28
    卓越
    -1.27
     otras
    -1.27
     gratuit
    -1.26
     cheveux
    -1.25
    tism
    -1.23
    POSITIVE LOGITS
     who
    1.75
     after
    1.70
     in
    1.66
     using
    1.52
     into
    1.48
     and
    1.45
     increase
    1.45
     when
    1.42
     eventually
    1.38
     hence
    1.32
    Activations Density 0.011%

    No Known Activations