© 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. 39127
    Prev
    Next
    INDEX
    Explanations

    Programming keywords and file types

    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
     laço
    -1.41
     této
    -1.39
    řejmě
    -1.38
     materiál
    -1.37
     tohoto
    -1.34
     cóc
    -1.33
     extremely
    -1.32
    wonderful
    -1.30
    discussion
    -1.30
     arreglos
    -1.25
    POSITIVE LOGITS
     també
    1.52
     is
    1.39
     tahun
    1.34
    вам
    1.33
     նաև
    1.32
     can
    1.22
    приєм
    1.21
    Another
    1.19
    What
    1.19
     what
    1.19
    Activations Density 0.199%

    No Known Activations