© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103685
    Prev
    Next
    INDEX
    Explanations

    once followed by past participle

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

    The neuron detects words and phrases that signal a subject’s former status or past distinction (e.g. “once,” “touted as,” “considered”).

    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
    溦
    -1.44
     soportes
    -1.38
     ersten
    -1.36
    according
    -1.35
     megfelelő
    -1.34
    currently
    -1.34
     currently
    -1.30
    歘
    -1.30
     chinh
    -1.30
     tamaños
    -1.29
    POSITIVE LOGITS
     about
    1.41
     pido
    1.36
    Once
    1.33
     should
    1.30
     a
    1.28
     might
    1.27
    aría
    1.27
    ৄ
    1.27
     Wisata
    1.23
    Ꮀ
    1.23
    Activations Density 0.023%

    No Known Activations