© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101770
    Prev
    Next
    INDEX
    Explanations

    directed graphs

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

    the word "directed" in technical contexts related to graphs and networks.

    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
    時は
    -2.17
     need
    -2.11
    er
    -1.95
    どちら
    -1.84
     jeweiligen
    -1.83
     freaking
    -1.78
     hinder
    -1.77
     {
    -1.75
    ⚋
    -1.73
    vement
    -1.73
    POSITIVE LOGITS
     and
    2.34
    錞
    1.77
     nimmer
    1.75
     saine
    1.74
    damento
    1.73
     土産
    1.73
     firft
    1.72
    vestres
    1.69
     水果
    1.66
     eenige
    1.66
    Activations Density 0.022%

    No Known Activations