© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48900
    Prev
    Next
    INDEX
    Explanations

    grandchildren and offspring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ço
    0.41
    母親
    0.40
    اوار
    0.39
    и
    0.39
    educated
    0.38
    prot
    0.38
    ଐ
    0.38
    ạp
    0.38
     образование
    0.38
     ১৯৬৫
    0.37
    POSITIVE LOGITS
     newborns
    0.48
     малы
    0.48
     newborn
    0.44
     newest
    0.44
     Tattoo
    0.43
     newcomers
    0.42
     Newborn
    0.42
     grandson
    0.41
     baby
    0.41
     cháu
    0.41
    Activations Density 0.012%

    No Known Activations