© 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. 81216
    Prev
    Next
    INDEX
    Explanations

    members of groups

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

    This neuron detects occurrences of the phrase “members 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
    部分
    -1.04
    もあって
    -0.94
     hài
    -0.92
     новые
    -0.91
     where
    -0.91
    ジナル
    -0.91
     indicative
    -0.90
    个
    -0.89
    Where
    -0.89
    もあった
    -0.87
    POSITIVE LOGITS
     the
    2.13
     staff
    1.52
     parliament
    1.47
     our
    1.39
     his
    1.24
     society
    1.23
     clergy
    1.16
     academia
    1.13
     keluarga
    1.11
     Parliament
    1.10
    Activations Density 0.024%

    No Known Activations