© 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. 10-GEMMASCOPE-RES-131K
    7. 42168
    Prev
    Next
    INDEX
    Explanations

    heaven, hell, or heavenly concepts

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

    The neuron responds to words referring to grand cosmic or religious spaces and entities (e.g. heaven, earth, universe, creation, mansion).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    魮
    -1.90
    垍
    -1.63
    皤
    -1.54
    そういえば
    -1.52
     socc
    -1.49
    毉
    -1.48
     lcm
    -1.48
    羕
    -1.46
    eluarkan
    -1.43
     コラボ
    -1.43
    POSITIVE LOGITS
     "
    2.38
     otras
    1.89
     nuevas
    1.70
     
    1.64
     dichas
    1.63
    "
    1.59
    .
    1.56
     s
    1.50
     outras
    1.50
    新型
    1.48
    Activations Density 0.006%

    No Known Activations