© 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. 12174
    Prev
    Next
    INDEX
    Explanations

    pseudo and proto prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or taxonomic names, particularly genus names and technical terminology in biology and chemistry.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     to
    -1.73
    がこの
    -1.66
     by
    -1.59
     Otros
    -1.59
    silueta
    -1.51
     into
    -1.51
     this
    -1.48
    毬
    -1.48
     with
    -1.47
    ',
    -1.47
    POSITIVE LOGITS
     vatten
    1.61
    m
    1.56
    ца
    1.51
     και
    1.51
     banyo
    1.48
     aksesuar
    1.48
     elegancia
    1.47
     cordones
    1.45
    s
    1.45
     çanta
    1.43
    Activations Density 0.181%

    No Known Activations