© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6918
    Prev
    Next
    INDEX
    Explanations

    old people, grandmother, or specific older individuals

    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_16k_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
     boyfriend
    0.51
     Boyfriend
    0.51
    男友
    0.49
     xinh
    0.47
    男朋友
    0.47
     جول
    0.46
     ٢
    0.43
     Industrial
    0.43
     Girlfriend
    0.43
     girlfriend
    0.43
    POSITIVE LOGITS
    老人
    0.98
    老年
    0.98
     retired
    0.97
    👵
    0.97
     elderly
    0.96
     emeritus
    0.95
     retiree
    0.91
    👴
    0.91
    高齢
    0.90
     dementia
    0.89
    Activations Density 0.258%

    No Known Activations