© 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. 92441
    Prev
    Next
    INDEX
    Explanations

    one or another

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

    This neuron fires on the recurring “one … another/other” pattern (e.g. “at one time or another,” “one after the other”).

    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
     also
    -1.16
     opposite
    -0.99
     similarly
    -0.96
     altrett
    -0.90
     equally
    -0.89
     another
    -0.89
    อีก
    -0.87
     również
    -0.81
     arī
    -0.81
    sig
    -0.81
    POSITIVE LOGITS
    other
    1.14
     the
    1.08
     other
    1.05
     autres
    0.97
     OTHER
    0.94
     andere
    0.93
     anderen
    0.93
     innymi
    0.92
     konstru
    0.90
     innych
    0.90
    Activations Density 0.018%

    No Known Activations