© 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. 10-GEMMASCOPE-RES-131K
    4. 104451
    Prev
    Next
    INDEX
    Explanations

    age and age ranges

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

    The neuron detects numeric age expressions (mentions of a person’s age, especially “age of/over/under” followed by a number).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     coiffure
    -1.54
    らしいです
    -1.51
     Ambas
    -1.48
    笮
    -1.48
     antropo
    -1.48
     islamic
    -1.46
     bollywood
    -1.42
    などなど
    -1.42
     chevy
    -1.41
     korean
    -1.40
    POSITIVE LOGITS
     than
    2.14
    ↵
    1.88
    </b>
    1.73
    ،
    1.73
    breviations
    1.71
    </h1>
    1.66
    ти
    1.64
    </
    1.58
    sians
    1.58
     \
    1.54
    Activations Density 0.006%

    No Known Activations