© 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. 269
    Prev
    Next
    INDEX
    Explanations

    code headers and definitions

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

    The neuron strongly activates on any token containing digits—e.g. numeric literals or identifiers with numbers.

    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
    Frm
    -0.77
     MOU
    -0.75
    Algo
    -0.75
     ऑ
    -0.74
     fuc
    -0.73
     Dan
    -0.73
     hype
    -0.73
     sickening
    -0.72
     бер
    -0.72
     Giga
    -0.72
    POSITIVE LOGITS
     akku
    0.96
    mvh
    0.91
     menj
    0.90
    ")}
    0.89
    Parent
    0.88
    );
    0.86
     вересня
    0.85
    クロー
    0.85
     протягом
    0.84
     kiu
    0.84
    Activations Density 0.019%

    No Known Activations