© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32431
    Prev
    Next
    INDEX
    Explanations

    age and aging

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

    discussions about age and aging, particularly in relation to physical or cognitive changes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on words and numbers referring to age or aging (e.g. “age,” “aging,” “old,” and numerical age references).

    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
     autism
    -0.86
     العلاج
    -0.82
    étation
    -0.80
    trique
    -0.80
    enschein
    -0.80
    iritto
    -0.79
    iforme
    -0.79
     '*')
    -0.79
    eroen
    -0.78
     Thakur
    -0.78
    POSITIVE LOGITS
     age
    3.08
     aging
    2.34
     Age
    2.27
     retirement
    2.25
     aged
    2.17
     ageing
    2.17
    Age
    2.14
     younger
    2.08
     youthful
    2.02
     Aging
    1.95
    Activations Density 0.136%

    No Known Activations