© 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. 34-GEMMASCOPE-RES-131K
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    assimilation and integration

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

    The neuron strongly activates on occurrences of “Borg” (and related references like “Borg drone”), i.e. mentions of that specific Star Trek entity.

    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
     Эти
    -0.93
    Kedves
    -0.80
    關係
    -0.77
     distribuição
    -0.77
     matured
    -0.76
     poë
    -0.76
    archical
    -0.75
    र्ड
    -0.75
    EDAD
    -0.75
     esthétique
    -0.75
    POSITIVE LOGITS
     assimilation
    4.25
    assim
    3.72
     Assim
    3.53
     assimilate
    3.42
     assimil
    3.33
    Assim
    3.27
     assimilated
    3.23
     assim
    2.59
     asim
    1.92
     integration
    1.67
    Activations Density 0.033%

    No Known Activations