© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20341
    Prev
    Next
    INDEX
    Explanations

    young males

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

    The neuron fires on words naming or referring to young people (e.g. child‐ or youth-related terms such as boy, girl, kid, teen, youth).

    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
    </h4>
    -1.60
    >
    -1.46
    se
    -1.45
    呖
    -1.45
     -
    -1.43
    </sup>
    -1.38
     same
    -1.34
    ↵↵
    -1.33
    相同
    -1.33
     by
    -1.30
    POSITIVE LOGITS
     aprende
    1.64
     who
    1.61
    ceptable
    1.58
     haremos
    1.52
     několika
    1.48
    Här
    1.45
    Kritik
    1.45
    віта
    1.41
    何故
    1.39
    cribing
    1.38
    Activations Density 0.144%

    No Known Activations