© 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. 64050
    Prev
    Next
    INDEX
    Explanations

    life and mortality insurance

    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
     burlap
    0.43
     hil
    0.42
     Nickelodeon
    0.42
     Спа
    0.41
    損
    0.40
     Impro
    0.39
    িব
    0.38
     Brake
    0.38
     ক্রমা
    0.38
     Yacht
    0.38
    POSITIVE LOGITS
     deceased
    0.50
     murdered
    0.46
     tissue
    0.46
    👪
    0.44
     मृतक
    0.44
     pituitary
    0.42
     meninggal
    0.42
     사망
    0.42
     mortality
    0.42
     Tissue
    0.42
    Activations Density 0.020%

    No Known Activations