© 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. 69102
    Prev
    Next
    INDEX
    Explanations

    previous or others

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

    The neuron detects sequence-oriented/ordinal markers (words that indicate order or steps, like “first,” “previous,” “another,” “secondary,” etc.).

    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
     such
    -0.97
     trong
    -0.90
     among
    -0.87
     beyond
    -0.86
    windigkeit
    -0.85
    身に
    -0.84
     kerül
    -0.84
     within
    -0.83
     polskich
    -0.81
    랐
    -0.81
    POSITIVE LOGITS
     previous
    1.84
     others
    1.73
     предыду
    1.62
    Others
    1.38
    previous
    1.32
    Previous
    1.21
     précédente
    1.17
    others
    1.16
     preceding
    1.11
     poprzed
    1.07
    Activations Density 0.085%

    No Known Activations