© 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. 34-GEMMASCOPE-RES-131K
    7. 75970
    Prev
    Next
    INDEX
    Explanations

    previous dates or numbers

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

    The neuron is triggered by numeric version strings or date‐style number sequences (e.g. “0.7.1,” “2015‐04‐20,” “2.1.7”) in technical changelogs or metadata.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     later
    -1.38
     subsequent
    -1.10
     später
    -1.06
     again
    -1.06
     senere
    -0.97
     successivo
    -0.97
     igjen
    -0.94
    后续
    -0.94
     później
    -0.93
     luego
    -0.91
    POSITIVE LOGITS
     предыду
    1.80
     sebelumnya
    1.80
     earlier
    1.64
     previous
    1.64
     preceding
    1.55
     anteriores
    1.45
     vorher
    1.42
     precedente
    1.39
    earlier
    1.31
    Earlier
    1.30
    Activations Density 0.122%

    No Known Activations