© 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. 9610
    Prev
    Next
    INDEX
    Explanations

    family members

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

    The neuron activates on words referring to one’s children—specifically “son” or “daughter.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of a speaker’s children, especially first-person possessive references to sons or daughters.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to the speaker's son or daughter in personal narratives.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    :
    -1.55
    䊐
    -1.46
     for
    -1.32
    bzw
    -1.24
     یا
    -1.23
     undermines
    -1.22
    ,
    -1.18
    !
    -1.15
    /
    -1.15
    หรือ
    -1.15
    POSITIVE LOGITS
     also
    1.86
     также
    1.30
     finally
    1.25
     even
    1.24
     semelhantes
    1.20
     similarly
    1.20
     vollständige
    1.20
     Phòng
    1.17
     sogen
    1.16
     également
    1.16
    Activations Density 0.035%

    No Known Activations