© 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. 36306
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron mainly activates on numeric tokens (digits, numbers, and numeric expressions).

    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
     while
    -1.85
     for
    -1.48
     would
    -1.47
     during
    -1.44
    satunya
    -1.42
     could
    -1.38
     when
    -1.28
     During
    -1.24
     might
    -1.19
     others
    -1.19
    POSITIVE LOGITS
     télécharger
    1.33
     genoux
    1.31
     corriger
    1.26
     enlever
    1.26
     appliquer
    1.25
    鵙
    1.23
    elded
    1.21
     cancelamento
    1.20
     équipements
    1.19
    落在
    1.18
    Activations Density 0.041%

    No Known Activations