© 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. 103331
    Prev
    Next
    INDEX
    Explanations

    past perfect verb forms

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

    The neuron almost exclusively lights up on the auxiliary “had,” detecting that specific past‐tense word.

    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
     and
    -1.66
     сейчас
    -1.29
     is
    -1.20
    тори
    -1.16
    quelles
    -1.16
     affichés
    -1.13
     capitulo
    -1.13
    Currently
    -1.10
     has
    -1.09
    turning
    -1.07
    POSITIVE LOGITS
     been
    3.00
     earlier
    2.19
     originally
    2.16
     hoped
    2.02
     previously
    1.84
     initially
    1.81
     gotten
    1.70
     begun
    1.55
     to
    1.53
     intended
    1.49
    Activations Density 0.036%

    No Known Activations