© 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. 19439
    Prev
    Next
    INDEX
    Explanations

    government actions and initiatives

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

    The neuron detects references to government or regulatory bodies and their actions (e.g., “government,” “regulations,” “initiatives,” “official”).

    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
    Donkey
    -1.45
     любого
    -1.45
    łość
    -1.37
    ercicio
    -1.30
     outspoken
    -1.30
    Scénario
    -1.30
    𝑿
    -1.27
    Exeunt
    -1.27
    pijama
    -1.27
    upaten
    -1.27
    POSITIVE LOGITS
     and
    1.76
    <b>
    1.31
    ych
    1.12
    Same
    1.12
    IA
    1.10
    ICA
    1.09
    んだから
    1.09
    想不到
    1.08
     do
    1.07
     apparaat
    1.04
    Activations Density 0.042%

    No Known Activations