© 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. 19200
    Prev
    Next
    INDEX
    Explanations

    "of" followed by possessives or "the"

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

    The neuron detects occurrences of the phrase “Friends of the …” as part of organization or title names.

    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
    \
    -1.70
     некоторые
    -1.48
     после
    -1.48
     если
    -1.46
    判斷
    -1.45
     desee
    -1.41
    jenigen
    -1.40
     После
    -1.39
    .
    -1.39
     Providing
    -1.37
    POSITIVE LOGITS
     of
    1.78
     ſol
    1.57
    櫪
    1.43
    霂
    1.43
    穽
    1.41
    ࿙
    1.41
    狴
    1.41
     طریق
    1.40
     houſe
    1.40
     fashioned
    1.36
    Activations Density 0.010%

    No Known Activations