© 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. 34-GEMMASCOPE-RES-131K
    7. 73550
    Prev
    Next
    INDEX
    Explanations

    demographic proportions of age

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

    The neuron fires on numeric tokens—table and figure numbers, years, statistical values, percentages, and other numerals.

    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
    煲
    -1.13
    androidx
    -1.03
    itys
    -1.00
    veck
    -0.98
    mapStateToProps
    -0.98
     سلام
    -0.98
    entibus
    -0.97
     foran
    -0.94
    StringBuilder
    -0.94
    visation
    -0.94
    POSITIVE LOGITS
     Census
    1.46
     age
    1.45
     households
    1.40
     males
    1.33
    Census
    1.26
     persons
    1.24
     census
    1.21
     female
    1.20
     urban
    1.18
    Persons
    1.17
    Activations Density 0.054%

    No Known Activations