© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6169
    Prev
    Next
    INDEX
    Explanations

    retire, retired, retirement

    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_40_width_262k_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
     intermediate
    0.50
     headway
    0.44
     Intermediate
    0.41
     SAR
    0.40
     homogeneous
    0.40
    瞬
    0.39
    Intermediate
    0.39
     Boyfriend
    0.39
     Educational
    0.38
     x
    0.38
    POSITIVE LOGITS
     retirement
    2.39
     retired
    2.38
     retire
    2.20
     retiring
    2.13
    退休
    2.13
    retired
    2.13
    retirement
    2.11
     retires
    2.08
     Retired
    2.05
    Retired
    2.00
    Activations Density 0.019%

    No Known Activations