© 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. 34-GEMMASCOPE-RES-131K
    7. 78232
    Prev
    Next
    INDEX
    Explanations

    resurrected, revived, returns from death

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

    This neuron flags mentions of death, dying, and revival (e.g. death, dead, revive, resurrected).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Repository
    -0.78
     Realty
    -0.78
    卸载
    -0.72
    ց
    -0.72
    filtration
    -0.72
    上去
    -0.71
    Ie
    -0.69
    فية
    -0.69
     nowy
    -0.68
     zeigten
    -0.68
    POSITIVE LOGITS
     resurrection
    3.97
     resurrected
    3.19
     resurrect
    3.09
     Resurrection
    2.98
     resurre
    2.84
     revive
    2.47
    復活
    2.39
     revival
    2.33
     воск
    2.31
     revived
    2.17
    Activations Density 0.025%

    No Known Activations