© 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. 34-GEMMASCOPE-RES-131K
    7. 23737
    Prev
    Next
    INDEX
    Explanations

    mother-in-law

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

    The neuron activates specifically on occurrences of the compound term “mother-in-law.”

    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
    psum
    -0.82
    xid
    -0.79
    urno
    -0.79
    íba
    -0.75
    INFINITY
    -0.73
    ママ
    -0.73
    xus
    -0.71
    ltr
    -0.71
    oteur
    -0.71
    ulis
    -0.70
    POSITIVE LOGITS
     mother
    2.59
     father
    2.33
     Mother
    2.17
    mother
    2.08
     Father
    2.02
    Mother
    1.96
    Father
    1.77
    father
    1.73
    MOTHER
    1.42
     MOTHER
    1.41
    Activations Density 0.014%

    No Known Activations