© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    family members communicating

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

    The neuron activates on mention of family relationships or kinship terms (e.g. father, mother, sister, family).

    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
     zarówno
    -1.45
     our
    -1.42
     naše
    -1.34
     nuestros
    -1.31
     nuestras
    -1.30
     about
    -1.29
     solchen
    -1.27
     nuestro
    -1.25
     både
    -1.25
     new
    -1.24
    POSITIVE LOGITS
     also
    1.53
     each
    1.25
    起來
    1.16
     zui
    1.12
    ませて
    1.09
     useRef
    1.09
     loue
    1.09
    起码
    1.09
     founded
    1.08
    话说
    1.07
    Activations Density 0.054%

    No Known Activations