© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103654
    Prev
    Next
    INDEX
    Explanations

    sports tournaments

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

    The neuron specializes in detecting numeric tokens (years, edition numbers, and similar 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
    abrigo
    -0.82
     Partei
    -0.76
     refus
    -0.74
    侦
    -0.74
    getTag
    -0.73
    ᱙
    -0.73
     Pires
    -0.73
    اوى
    -0.72
    árd
    -0.72
    дьми
    -0.72
    POSITIVE LOGITS
     Copa
    1.26
     Gold
    1.05
    Copa
    0.94
     CON
    0.88
    Gold
    0.87
     Guest
    0.79
     gold
    0.76
    nation
    0.75
    Guest
    0.75
    CON
    0.73
    Activations Density 0.024%

    No Known Activations