© 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. 86897
    Prev
    Next
    INDEX
    Explanations

    following punctuation or 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
    .
    -1.76
    Including
    -1.58
     INFORMACIÓN
    -1.55
    鹩
    -1.54
     Verständnis
    -1.52
     favoriser
    -1.51
     bénéficier
    -1.50
     dismal
    -1.49
    栊
    -1.48
     occuper
    -1.48
    POSITIVE LOGITS
     nestled
    1.77
    '
    1.70
     with
    1.68
     epitom
    1.58
     misguided
    1.58
     enticing
    1.51
     burgeoning
    1.48
     facilitating
    1.48
     for
    1.45
     frightening
    1.43
    Activations Density 0.450%

    No Known Activations