© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73078
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by verbs

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

    The neuron detects auxiliary verbs used in perfect constructions (e.g., “has,” “have,” “been”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.77
     ketika
    -1.33
     عندما
    -1.29
     last
    -1.20
     cuando
    -1.17
     когда
    -1.08
     Ketika
    -1.06
     когато
    -1.06
     đã
    -1.05
     have
    -1.02
    POSITIVE LOGITS
    ૌ
    0.94
    ucket
    0.92
     Vaugh
    0.91
    Oltre
    0.91
    Oggi
    0.90
    別人
    0.87
    Scopri
    0.87
    bination
    0.86
    時間も
    0.86
    Grazie
    0.85
    Activations Density 0.089%

    No Known Activations