© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86620
    Prev
    Next
    INDEX
    Explanations

    words following numbers

    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
     insanların
    -1.43
    这样一个
    -1.34
    ophage
    -1.30
    着一个
    -1.29
     Cualquier
    -1.26
     продаже
    -1.26
    はは
    -1.25
     dintr
    -1.24
    何故
    -1.23
     När
    -1.22
    POSITIVE LOGITS
    ↵
    1.54
     last
    1.52
     earlier
    1.42
     further
    1.26
     additional
    1.22
     …
    1.20
     cost
    1.17
     will
    1.17
     Unies
    1.16
     already
    1.14
    Activations Density 0.124%

    No Known Activations