© 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. 60887
    Prev
    Next
    INDEX
    Explanations

    linking tokens by delimiters

    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
     поэтому
    -1.44
     häufig
    -1.38
     depiction
    -1.34
    riwal
    -1.33
     "
    -1.32
    鱟
    -1.31
     is
    -1.30
    <tbody>
    -1.29
    ']=='
    -1.28
    了一口气
    -1.27
    POSITIVE LOGITS
     that
    2.34
     others
    1.64
     such
    1.63
     other
    1.54
     those
    1.34
    到现在
    1.32
     either
    1.31
     lessen
    1.29
     their
    1.27
     are
    1.26
    Activations Density 0.755%

    No Known Activations