© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44325
    Prev
    Next
    INDEX
    Explanations

    regular expressions and data patterns

    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
    ਲ਼
    -1.71
    硖
    -1.53
     aeruginosa
    -1.45
    eeeee
    -1.44
    闓
    -1.42
    垵
    -1.41
     monta
    -1.41
    тся
    -1.34
    eeee
    -1.32
    ówka
    -1.30
    POSITIVE LOGITS
     impeded
    1.47
    好像是
    1.42
     почему
    1.41
    越多
    1.39
    当下
    1.39
     nueve
    1.38
     設備
    1.38
     who
    1.38
    There
    1.38
    何故
    1.38
    Activations Density 0.018%

    No Known Activations