© 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. 127187
    Prev
    Next
    INDEX
    Explanations

    boyfriend, husband, man, guy

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

    The neuron responds to words naming or referring to a specific male person in a personal relationship (e.g. boyfriend, husband, step-dad).

    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
    ones
    -1.36
     graden
    -1.30
    ____________
    -1.29
     traktor
    -1.23
     anden
    -1.23
     ELIZABETH
    -1.23
     vasi
    -1.21
     PENNSYLVANIA
    -1.20
     bela
    -1.20
     ria
    -1.20
    POSITIVE LOGITS
     Every
    1.27
    ˃
    1.24
    ˂
    1.22
     We
    1.20
     jsme
    1.19
     There
    1.19
     EVERY
    1.18
     сливо
    1.16
     It
    1.14
     As
    1.14
    Activations Density 0.044%

    No Known Activations