© 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. 119932
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

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

    line breaks or whitespace that precedes structural elements like list items, table rows, or formatted code sections.

    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
     so
    -2.16
     used
    -2.02
     was
    -1.91
     avoiding
    -1.83
     Because
    -1.83
     make
    -1.77
     refused
    -1.76
     As
    -1.71
     kept
    -1.71
     enhances
    -1.70
    POSITIVE LOGITS
    0
    2.00
     DIFFERENT
    1.76
     brill
    1.76
    6
    1.72
     två
    1.69
     pernic
    1.67
     pè
    1.65
     PERFECT
    1.63
     acqua
    1.63
     standalone
    1.62
    Activations Density 0.000%

    No Known Activations