© 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. 10-GEMMASCOPE-RES-131K
    7. 9057
    Prev
    Next
    INDEX
    Explanations

    past states or events

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

    The neuron strongly activates on past-tense or past-participle verbs (e.g. regular “-ed” forms and irregular past participles).

    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
    其妙
    -1.32
     MADISON
    -1.16
     fta
    -1.16
     持つ
    -1.13
     remember
    -1.13
    齶
    -1.13
     paulo
    -1.11
     eene
    -1.11
     ・
    -1.10
     krach
    -1.10
    POSITIVE LOGITS
     There
    1.42
     had
    1.30
     betreffenden
    1.26
    Either
    1.24
     entweder
    1.23
     там
    1.20
     has
    1.18
    Fußball
    1.16
     there
    1.16
     Empieza
    1.15
    Activations Density 0.083%

    No Known Activations