© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63562
    Prev
    Next
    INDEX
    Explanations

    aged, ages, aging

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

    The neuron responds to words containing the substring “age” (e.g. package, packaged, repackaged, coverage, leverages, unpackaged).

    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
    yendo
    -0.78
    haar
    -0.77
    掷
    -0.76
     Intel
    -0.72
    izable
    -0.71
     Dupont
    -0.70
    viseur
    -0.69
     április
    -0.69
     向
    -0.69
    uacute
    -0.69
    POSITIVE LOGITS
    age
    2.38
    ages
    1.99
    aged
    1.98
    AGE
    1.59
    aging
    1.55
    AGES
    1.50
    AGED
    1.31
    âge
    1.23
    ager
    1.19
     aged
    1.18
    Activations Density 0.055%

    No Known Activations