© 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. 10-GEMMASCOPE-RES-131K
    4. 19287
    Prev
    Next
    INDEX
    Explanations

    man, woman and human

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

    This neuron detects explicit references to being human or male, such as the words “human” and “man.”

    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
     or
    -1.73
    sejarah
    -1.39
     lecker
    -1.26
     süß
    -1.21
     the
    -1.19
     mädchen
    -1.15
     similar
    -1.14
     gebruikers
    -1.13
     serca
    -1.12
     oryginal
    -1.12
    POSITIVE LOGITS
    ☆、
    1.42
    even
    1.24
    since
    1.23
     inov
    1.19
     Manifesto
    1.18
    with
    1.17
     Deve
    1.16
    >');
    1.16
     メニュー
    1.16
    これからも
    1.15
    Activations Density 0.048%

    No Known Activations