© 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. 104618
    Prev
    Next
    INDEX
    Explanations

    Lois & Clark, Database Backup

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

    opening curly braces in LaTeX mathematical notation.

    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
     Both
    -2.09
     When
    -2.05
     Every
    -1.93
    ",
    -1.88
     Для
    -1.83
     Finally
    -1.80
     Clearly
    -1.77
     Regardless
    -1.76
     More
    -1.75
    瀟
    -1.74
    POSITIVE LOGITS
    {
    2.38
    </strong>
    2.22
     enorme
    1.90
     habitudes
    1.85
     discrepan
    1.84
     persecu
    1.77
     latine
    1.77
    鶿
    1.77
     morfo
    1.77
    疍
    1.76
    Activations Density 0.000%

    No Known Activations