© 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. 22-GEMMASCOPE-RES-131K
    4. 54210
    Prev
    Next
    INDEX
    Explanations

    geographical areas and places

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

    The neuron strongly activates on numeric expressions—i.e. tokens representing numbers, measurements, or quantities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     something
    -1.38
    alties
    -1.29
     erreichte
    -1.25
    config
    -1.23
     ilegal
    -1.23
     LIABLE
    -1.20
    lograph
    -1.20
     рис
    -1.19
    ⢸
    -1.18
     results
    -1.17
    POSITIVE LOGITS
     area
    1.63
     region
    1.48
     of
    1.45
     areas
    1.31
     district
    1.21
     oblasti
    1.20
     town
    1.18
    strtotime
    1.12
     country
    1.11
     vicinity
    1.10
    Activations Density 0.050%

    No Known Activations