© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    mortality, existentialism

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     घायल
    0.69
     সারাদেশ
    0.59
    批评
    0.59
     постра
    0.58
    癖
    0.57
    受伤
    0.55
     ಪೊಲೀಸ
    0.54
    哄
    0.54
     Hidden
    0.54
    🏘
    0.54
    POSITIVE LOGITS
     longevity
    1.66
     lifespan
    1.53
    寿命
    1.51
     immortality
    1.33
     shortening
    1.20
     mortality
    1.20
     عمر
    1.16
     prolongation
    1.16
     expiration
    1.16
     shorten
    1.15
    Activations Density 0.112%

    No Known Activations