© 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. 10-GEMMASCOPE-RES-131K
    7. 112656
    Prev
    Next
    INDEX
    Explanations

    past participles and passive voice

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

    The neuron fires on verbs—especially copulas (“is,” “was,” “be”) and past‐tense or past‐participle forms.

    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
     законода
    -1.42
     January
    -1.38
     new
    -1.30
     July
    -1.29
     December
    -1.23
    干脆
    -1.23
     —
    -1.23
    elte
    -1.20
    増加
    -1.20
     -
    -1.20
    POSITIVE LOGITS
    휀
    1.48
     volete
    1.41
     considerato
    1.39
     trovato
    1.34
    
    1.34
     jeito
    1.27
    浿
    1.27
     églises
    1.27
    não
    1.25
     costru
    1.24
    Activations Density 0.013%

    No Known Activations