© 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. 22-GEMMASCOPE-RES-131K
    7. 11235
    Prev
    Next
    INDEX
    Explanations

    replace swap exchange substitute

    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_22/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
    showAll
    -0.96
     sépar
    -0.82
    tikz
    -0.82
     tudo
    -0.81
    Ikke
    -0.80
     فيديو
    -0.79
     Ν
    -0.76
    Accent
    -0.75
     всем
    -0.74
     Bick
    -0.74
    POSITIVE LOGITS
     replace
    2.86
     replacement
    2.66
    replace
    2.50
     replacing
    2.45
     replaced
    2.45
    替换
    2.39
     replacements
    2.38
     Replace
    2.34
     replaces
    2.27
    Replace
    2.20
    Activations Density 0.078%

    No Known Activations