© 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. 34-GEMMASCOPE-RES-131K
    4. 115633
    Prev
    Next
    INDEX
    Explanations

    World of [entity] titles

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

    The neuron activates on the phrase “World of” (i.e. occurrences of “World” followed by “of”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    werkt
    -0.79
    kään
    -0.76
    stück
    -0.75
    Broad
    -0.74
    هل
    -0.74
    styleUrls
    -0.73
    نمای
    -0.72
     aliens
    -0.72
    Afghan
    -0.71
     Broad
    -0.70
    POSITIVE LOGITS
     hurt
    0.80
    ense
    0.76
     مورد
    0.73
    othelial
    0.68
    ヨーロ
    0.67
    猥
    0.66
    viera
    0.65
    总裁
    0.65
    sense
    0.65
     ferons
    0.65
    Activations Density 0.025%

    No Known Activations