© 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. 13060
    Prev
    Next
    INDEX
    Explanations

    code endings

    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
     alcuni
    -1.02
     alcune
    -0.98
    ellery
    -0.90
     certain
    -0.86
     certaines
    -0.86
    woofer
    -0.84
     Muchas
    -0.83
     sicherlich
    -0.83
     verão
    -0.83
     desejo
    -0.82
    POSITIVE LOGITS
    higen
    0.91
     perpetually
    0.90
    eca
    0.89
     extravagant
    0.87
    ylum
    0.87
    هرست
    0.85
    Sklici
    0.84
    ảy
    0.83
     draped
    0.82
     perplexing
    0.82
    Activations Density 0.025%

    No Known Activations