© 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. 73666
    Prev
    Next
    INDEX
    Explanations

    French cities and regions

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

    The neuron strongly activates on numeric tokens (sequences of digits), i.e. numbers 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
    お楽しみに
    -0.74
    杞
    -0.73
     sklo
    -0.68
    Loire
    -0.67
    ACIAS
    -0.67
     Affects
    -0.67
     جع
    -0.66
     czarna
    -0.66
    rupal
    -0.66
     forder
    -0.66
    POSITIVE LOGITS
     Cannes
    1.28
     Nice
    1.27
    Monaco
    0.99
     Monaco
    0.98
    Nice
    0.94
     NICE
    0.92
     Proven
    0.91
     Aix
    0.90
     Puget
    0.85
     atrás
    0.84
    Activations Density 0.009%

    No Known Activations