© 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. 22-GEMMASCOPE-RES-131K
    7. 9470
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

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

    This neuron fires on past-participial forms of verbs (i.e. words ending in “-ed”).

    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
    
    -1.49
    🔰
    -0.95
     héro
    -0.94
    MILLISECONDS
    -0.93
    WebElementEntity
    -0.90
    MAXN
    -0.90
     konsult
    -0.90
    ⬅
    -0.88
    arischen
    -0.88
    הפ
    -0.88
    POSITIVE LOGITS
     lã
    1.04
    ubber
    0.93
     nhung
    0.93
     therefore
    0.92
     모든
    0.92
    いただける
    0.91
     spojen
    0.91
     erwor
    0.90
     grossa
    0.90
     ámbitos
    0.90
    Activations Density 0.026%

    No Known Activations