© 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. 99615
    Prev
    Next
    INDEX
    Explanations

    transfer of power or control

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

    This neuron detects mentions of formal transfers or handovers of authority or control (e.g. “transfer of command,” “hand off control,” “take power”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    3
    -1.93
    4
    -1.58
    8
    -1.50
    1
    -1.45
    0
    -1.41
    7
    -1.39
    6
    -1.39
    {\
    -1.36
    ^{
    -1.32
    5
    -1.25
    POSITIVE LOGITS
     the
    1.80
     its
    1.33
     aprende
    1.30
    acea
    1.19
    च्च
    1.17
    izmus
    1.17
    dzić
    1.16
    ◆◇
    1.16
     dotyczą
    1.14
     one
    1.13
    Activations Density 0.033%

    No Known Activations