© 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. 19080
    Prev
    Next
    INDEX
    Explanations

    brother-in-law, sister-in-law

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

    The neuron fires on the word “law” when it appears as part of “in-law,” i.e. mentions of in-law relationships.

    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
    </em>
    -2.59
     allgemeine
    -2.08
    尛
    -1.98
    ࿚
    -1.95
     numerous
    -1.88
    这几
    -1.80
     privaten
    -1.80
     hochwer
    -1.77
    ICOLON
    -1.70
    ubahan
    -1.70
    POSITIVE LOGITS
    卺
    2.38
    I
    2.19
    ſſen
    2.06
     centrum
    1.95
    ;
    1.94
    去
    1.92
    ᆞ
    1.90
    们的
    1.85
     ſou
    1.84
     kardashian
    1.80
    Activations Density 0.002%

    No Known Activations