© 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. 90718
    Prev
    Next
    INDEX
    Explanations

    court cases and identifiers

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

    The main thing this neuron does is find numeric tokens (sequences of digits).

    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
     演
    -0.93
    ündung
    -0.82
    ミアム
    -0.80
    𝖒
    -0.75
    =}
    -0.73
     Violation
    -0.72
    čnosti
    -0.72
    BETWEEN
    -0.72
    ウター
    -0.71
     السابق
    -0.71
    POSITIVE LOGITS
    ;%%
    0.88
     poroz
    0.81
    манда
    0.81
     atento
    0.79
     Imágenes
    0.78
     последу
    0.78
     Unii
    0.77
     kilka
    0.76
     problemy
    0.76
     slid
    0.75
    Activations Density 0.086%

    No Known Activations