© 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. 50140
    Prev
    Next
    INDEX
    Explanations

    irish places and entities

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

    The neuron fires primarily on numeric tokens and figures (scores, dates, counts, and other digit sequences).

    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
    gul
    -0.81
    unique
    -0.77
    ʼn
    -0.77
    Irish
    -0.75
     پدر
    -0.73
     Gul
    -0.71
     Irish
    -0.69
    AddRange
    -0.68
     berpeng
    -0.67
     افراد
    -0.66
    POSITIVE LOGITS
    ítě
    0.85
     slay
    0.79
     MDR
    0.78
    iai
    0.76
     Peas
    0.75
     mụn
    0.75
     rapporte
    0.74
    álisis
    0.74
     상세
    0.72
    lamine
    0.72
    Activations Density 0.013%

    No Known Activations