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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14867
    Prev
    Next
    INDEX
    Explanations

    death, death dates, death penalty

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

    death sentence or threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     названия
    0.59
    atakse
    0.56
    ів
    0.56
    DR
    0.55
    QRY
    0.54
    㫙
    0.54
    ক্লা
    0.53
    amending
    0.53
     ສຳ
    0.53
    què
    0.53
    POSITIVE LOGITS
     death
    1.30
     muerte
    1.28
    death
    1.18
     Death
    1.16
     morte
    1.13
    死的
    1.09
    死
    1.05
     DEATH
    1.05
    Death
    1.02
     死
    1.00
    Activations Density 0.039%

    No Known Activations