© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130891
    Prev
    Next
    INDEX
    Explanations

    Adam and Eve stories

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

    This neuron selectively activates on key proper nouns and terms from biblical narratives—especially names of figures (e.g. Adam, Eve, Lucifer, Satan) and related scriptural places or events.

    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
    3
    -1.39
    six
    -1.37
    during
    -1.32
     -"
    -1.32
    available
    -1.32
    はこの
    -1.30
    www
    -1.30
    see
    -1.29
    self
    -1.29
    謦
    -1.28
    POSITIVE LOGITS
     curar
    1.38
    pantalón
    1.36
     frescas
    1.35
    法國
    1.31
     入っ
    1.30
    camiseta
    1.28
     agregado
    1.25
    ⛲
    1.24
     bonheur
    1.22
    ⪯
    1.22
    Activations Density 0.015%

    No Known Activations