© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58397
    Prev
    Next
    INDEX
    Explanations

    parents' actions and history

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

    The neuron detects mentions of parents’ life events or statuses (e.g. parents “worked,” “divorced,” “died”) in biographical text.

    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
    ▭
    -1.27
    átula
    -1.23
    began
    -1.23
    imetsu
    -1.22
    抜粋
    -1.22
    artements
    -1.17
    OrWhiteSpace
    -1.15
    brainly
    -1.15
     gbc
    -1.13
    citename
    -1.10
    POSITIVE LOGITS
     ผม
    1.13
     —
    1.12
     braccia
    1.07
     ruine
    1.05
     misteriosa
    1.04
     abbia
    1.03
     evangé
    1.02
     Água
    0.96
    </h3>
    0.95
     woods
    0.94
    Activations Density 0.120%

    No Known Activations