© 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. 81131
    Prev
    Next
    INDEX
    Explanations

    translation strings and plurals

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

    The neuron fires primarily on numeric literal tokens (sequences of digits) in code.

    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
     Fik
    -0.79
     UNEP
    -0.76
    undy
    -0.73
    ipen
    -0.73
    omé
    -0.73
    зать
    -0.71
     vš
    -0.71
    <0xD4>
    -0.69
     lucru
    -0.69
    消费者
    -0.68
    POSITIVE LOGITS
    plural
    0.96
     plural
    0.92
    singular
    0.89
    Singular
    0.87
    Plural
    0.83
     singular
    0.83
    Fmt
    0.82
    pover
    0.82
    colony
    0.81
    닫
    0.80
    Activations Density 0.038%

    No Known Activations