© 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. 39827
    Prev
    Next
    INDEX
    Explanations

    eternity, perpetuity, posterity, eternally

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

    This neuron detects words referring to unending or indefinite duration (e.g., eternity, perpetuity, posterity).

    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
    尨
    -2.75
    ଙ
    -2.45
    
    -2.39
    淠
    -2.36
    ?!?
    -2.34
     giv
    -2.31
    悄悄
    -2.25
    檍
    -2.25
    に行って
    -2.25
     駅前
    -2.25
    POSITIVE LOGITS
    c
    2.70
    ]
    2.47
    
    2.42
    呖
    2.41
    i
    2.38
    !
    2.36
    le
    2.30
    h
    2.27
    ="
    2.22
     Gegensatz
    2.20
    Activations Density 0.001%

    No Known Activations