© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4170
    Prev
    Next
    INDEX
    Explanations

    bodies found in disposal or burial

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

    The neuron fires on factual reporting of discovered human remains or murder victims (e.g. “unidentified,” “murder,” “victim,” “discovered,” dates/locations).

    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
     junctions
    -0.84
    inhua
    -0.83
     confiscated
    -0.80
     зави
    -0.79
    junction
    -0.78
    ში
    -0.77
     Nha
    -0.75
     hemis
    -0.75
    mientras
    -0.74
     ツ
    -0.72
    POSITIVE LOGITS
     disposal
    1.27
     dump
    1.23
     dumping
    1.15
    dump
    1.14
     decomposition
    1.14
     dumped
    1.12
     decompose
    1.11
     decomposed
    1.10
     Dump
    1.09
     decom
    1.02
    Activations Density 0.020%

    No Known Activations