© 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. 20178
    Prev
    Next
    INDEX
    Explanations

    HTML tags, names, numbers, Q&A format

    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
     extremadamente
    -1.22
     auténtica
    -1.20
    ساء
    -1.20
     find
    -1.19
     benzer
    -1.16
    ajuku
    -1.14
     embrague
    -1.13
     प्रमुख
    -1.13
     atractiva
    -1.13
     if
    -1.13
    POSITIVE LOGITS
     that
    1.93
     they
    1.50
    攵
    1.38
     serre
    1.30
     innan
    1.28
     säga
    1.27
     vider
    1.27
    趿
    1.26
     ciment
    1.26
     circon
    1.25
    Activations Density 0.000%

    No Known Activations