© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    burial places

    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
     প্রয
    0.44
     ধরা
    0.43
     repeatable
    0.38
    Swim
    0.38
     swimsuit
    0.38
     এজ
    0.38
    splits
    0.38
    鹜
    0.37
    锏
    0.37
    流水
    0.36
    POSITIVE LOGITS
     cemetery
    2.36
     burial
    2.23
     cemeteries
    2.23
    墓
    2.09
     burials
    2.08
     graves
    2.05
     Cemetery
    1.98
     graveyard
    1.97
     Burial
    1.87
     tombs
    1.83
    Activations Density 0.013%

    No Known Activations