© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65914
    Prev
    Next
    INDEX
    Explanations

    death and killing

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

    references to death or dying in news reports.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words and phrases that denote death or being killed (e.g., died, dead, killed, passed away).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.17
     vždy
    -1.11
    uves
    -1.06
    arh
    -1.06
    brium
    -1.05
     annually
    -1.03
    rlpool
    -1.03
     continually
    -1.03
    idjan
    -1.02
     and
    -1.00
    POSITIVE LOGITS
     shortly
    1.29
     after
    1.17
     Internasional
    1.12
     Thursday
    1.11
    детская
    1.10
    Shortly
    1.09
    节日
    1.07
    MatIconModule
    1.05
     three
    1.03
    Недо
    1.03
    Activations Density 0.013%

    No Known Activations