© 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. 10-GEMMASCOPE-RES-131K
    7. 128750
    Prev
    Next
    INDEX
    Explanations

    Amen, Amin, amend, orrhea, Karyometry

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

    The neuron fires on any token containing the letter sequence “amen.”

    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
    翃
    -3.11
    轳
    -2.73
     všech
    -2.73
    нимание
    -2.53
    くらいの
    -2.48
    倌
    -2.48
    戩
    -2.42
     legions
    -2.42
    
    -2.42
     unsuspecting
    -2.41
    POSITIVE LOGITS
    .
    3.38
    镦
    2.78
    ↵↵
    2.67
    We
    2.45
    鯪
    2.28
     barca
    2.17
    簓
    2.17
    蟊
    2.09
    涠
    2.06
    蹕
    2.06
    Activations Density 0.007%

    No Known Activations