© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7930
    Prev
    Next
    INDEX
    Explanations

    no death

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags references to death or violent casualties—words naming victims, wounds, gunshots, or dead bodies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     Baillargeon
    0.60
    幼稚園
    0.56
     alerg
    0.55
     reproduces
    0.55
    霹
    0.54
    льності
    0.54
    слови
    0.53
     harass
    0.53
     intimid
    0.53
    íamos
    0.52
    POSITIVE LOGITS
     corpses
    2.16
    屍
    2.14
     cadáver
    2.08
     corpse
    2.06
    尸
    1.96
     लाश
    1.88
     লাশ
    1.79
     शव
    1.78
     carcasses
    1.74
     মরদেহ
    1.69
    Activations Density 0.310%

    No Known Activations