© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7459
    Prev
    Next
    INDEX
    Explanations

    death and disposal

    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
     aufgebaut
    0.42
     (%
    0.41
     الدا
    0.40
     कुशवाहा
    0.40
     ejercicios
    0.39
     exploits
    0.39
    AllCaps
    0.38
    间
    0.38
    ➠
    0.38
    观点
    0.38
    POSITIVE LOGITS
     burial
    1.01
     funeral
    0.85
     Burial
    0.81
     शव
    0.80
     corpse
    0.80
     মরদেহ
    0.79
     cremation
    0.79
     cadáver
    0.79
     embal
    0.78
     coroner
    0.78
    Activations Density 0.046%

    No Known Activations