© 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. 20645
    Prev
    Next
    INDEX
    Explanations

    funeral and condolence contexts

    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
     hirs
    0.46
     ზე
    0.46
    ಙ
    0.46
     wund
    0.45
    🐸
    0.42
     conosci
    0.41
    Checksum
    0.41
    InfoWindow
    0.41
     weet
    0.40
     oxidize
    0.40
    POSITIVE LOGITS
     obituary
    0.62
     funeral
    0.62
     Funeral
    0.54
    Funeral
    0.53
     funerals
    0.51
     Obituary
    0.47
     burial
    0.44
    訃
    0.43
     recipient
    0.43
     predeceased
    0.43
    Activations Density 0.006%

    No Known Activations