© 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. 95353
    Prev
    Next
    INDEX
    Explanations

    previous or preceding

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

    The neuron fires on words that denote relative ordering or reference to an earlier item in a sequence (e.g. “previous,” “preceding,” “before,” “less than,” “from”).

    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
    これから
    -1.02
    以後
    -0.93
    现代
    -0.88
     nachfol
    -0.88
    liseum
    -0.86
     бере
    -0.86
    بعد
    -0.86
    ウエ
    -0.84
    Later
    -0.84
     tardi
    -0.82
    POSITIVE LOGITS
     prior
    1.45
     previous
    1.42
     preceding
    1.40
     earlier
    1.20
     Prior
    1.09
    previous
    1.08
     before
    1.07
    cześ
    1.05
     sebelumnya
    1.05
     previo
    1.02
    Activations Density 0.025%

    No Known Activations