© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83978
    Prev
    Next
    INDEX
    Explanations

    age of items and beings

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

    The neuron detects numeric age or time indicators (mentions of ages, years, or durations).

    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
     "
    -1.73
    <bos>
    -1.53
     clín
    -1.42
    髣
    -1.42
    鮋
    -1.35
    rieren
    -1.34
    合わせて
    -1.34
     idén
    -1.32
    彡
    -1.29
     ("
    -1.28
    POSITIVE LOGITS
     and
    1.84
     age
    1.77
    Ꮟ
    1.58
    old
    1.58
    、
    1.46
     medlemmer
    1.45
     プール
    1.40
     vieux
    1.39
     old
    1.36
    Ｑ
    1.36
    Activations Density 0.083%

    No Known Activations