© 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. 22-GEMMASCOPE-RES-131K
    7. 28577
    Prev
    Next
    INDEX
    Explanations

    Numbers and specific items

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

    The neuron primarily responds to numeric expressions and quantitative data (numbers, measurements, statistics).

    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
     envelo
    -1.77
     blancs
    -1.61
     réfrig
    -1.59
     ámbitos
    -1.57
     logiciels
    -1.54
     rabat
    -1.53
     chers
    -1.53
     téléph
    -1.53
     dessins
    -1.52
    sont
    -1.52
    POSITIVE LOGITS
    There
    2.02
     There
    1.79
    What
    1.73
    It
    1.72
    Before
    1.70
     In
    1.69
    You
    1.69
     It
    1.67
     has
    1.63
     Before
    1.59
    Activations Density 0.574%

    No Known Activations