© 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. 34-GEMMASCOPE-RES-131K
    4. 34725
    Prev
    Next
    INDEX
    Explanations

    identifying age

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

    This neuron activates on hyphenated age expressions, i.e. “[number]-year-old” phrases.

    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
     \&
    -1.17
     and
    -1.02
     seseorang
    -0.94
    ังก
    -0.89
     sekä
    -0.88
    }[!
    -0.88
    って何
    -0.88
     seorang
    -0.86
    mpf
    -0.85
     तथा
    -0.84
    POSITIVE LOGITS
    穌
    1.03
     نے
    0.94
     eterna
    0.93
    pography
    0.92
     former
    0.88
    Уже
    0.87
     luf
    0.86
    즘
    0.85
     Alamy
    0.85
     Bett
    0.85
    Activations Density 0.013%

    No Known Activations