© 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. 10-GEMMASCOPE-RES-131K
    7. 73338
    Prev
    Next
    INDEX
    Explanations

    young age

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

    The neuron detects mentions of a person’s age, especially phrases like “at a young age” or “early age.”

    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
    ).
    -1.85
    荦
    -1.77
    ൎ
    -1.68
    ’)
    -1.63
     :}
    -1.51
    柰
    -1.51
    ୩
    -1.49
     murs
    -1.49
    ichteten
    -1.48
    ︒
    -1.47
    POSITIVE LOGITS
     его
    2.17
    8
    2.02
     нескольких
    1.97
    7
    1.89
    他
    1.88
     it
    1.88
     of
    1.87
    9
    1.78
     эти
    1.75
    6
    1.73
    Activations Density 0.005%

    No Known Activations