© 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. 26037
    Prev
    Next
    INDEX
    Explanations

    circuit judges

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

    This neuron detects imperative‐style action verbs in technical documentation (e.g. “Synchronize,” “writes,” “should,” “done”)—i.e. the instruction language of man pages and config guides.

    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
    Offline
    -0.71
     chancel
    -0.71
     Handball
    -0.71
     liens
    -0.69
     Chantal
    -0.67
     realist
    -0.66
    ッシャー
    -0.65
     кроме
    -0.65
     drones
    -0.65
     flamenco
    -0.65
    POSITIVE LOGITS
     классов
    0.71
    uert
    0.70
    czego
    0.67
    SerializedSize
    0.66
    겁
    0.65
     Wenn
    0.65
    rias
    0.64
     Virginia
    0.64
    bino
    0.64
     ป
    0.63
    Activations Density 0.077%

    No Known Activations