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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8147
    Prev
    Next
    INDEX
    Explanations

    grandparents and parents

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

    grandparents, grandmothers, grandfathers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سیک
    0.38
     browser
    0.38
     เด่น
    0.37
    etten
    0.36
    teryx
    0.36
    odiac
    0.36
    ධ
    0.35
     শৃ
    0.35
     camber
    0.34
     despe
    0.33
    POSITIVE LOGITS
     Grandma
    3.63
     grandma
    3.56
     grandpa
    3.55
     Grandmother
    3.53
     Grandpa
    3.52
     grandfather
    3.42
     grandmother
    3.38
     grandparents
    3.31
     grandparent
    3.25
    爷爷
    3.16
    Activations Density 0.109%

    No Known Activations