© 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. 56033
    Prev
    Next
    INDEX
    Explanations

    national

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers and years—in the text.

    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
    ını
    -0.75
     Hang
    -0.75
     schwier
    -0.74
     all
    -0.74
     lessen
    -0.73
    ذف
    -0.72
    徳
    -0.72
     actualmente
    -0.72
     Ng
    -0.71
    shit
    -0.71
    POSITIVE LOGITS
     AVEN
    0.81
    ∐
    0.81
    Sog
    0.79
     Utica
    0.77
     SCHE
    0.77
    Auditor
    0.77
     STAM
    0.76
    谜
    0.76
     RUT
    0.75
    kém
    0.75
    Activations Density 0.003%

    No Known Activations