© 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. 34-GEMMASCOPE-RES-131K
    4. 38681
    Prev
    Next
    INDEX
    Explanations

    verb forms of 'have'

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

    This neuron spotlights occurrences of the auxiliary verb “have” (in its various forms: have, has, had, hath).

    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
    tambah
    -0.94
    pista
    -0.89
     has
    -0.84
    redmi
    -0.83
    ťaž
    -0.82
    nelson
    -0.81
    Eles
    -0.81
     would
    -0.79
    salomon
    -0.79
    activa
    -0.79
    POSITIVE LOGITS
     been
    1.10
     recourse
    1.00
     not
    0.97
     incurred
    0.96
     done
    0.90
    before
    0.89
    idhi
    0.89
     before
    0.87
     где
    0.86
     AssemblyTitle
    0.86
    Activations Density 0.016%

    No Known Activations