© 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. 7847
    Prev
    Next
    INDEX
    Explanations

    being subject or state

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

    The neuron is triggered by occurrences of the word “being.”

    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
    j
    -3.16
    )();
    -2.72
    WRENCE
    -2.63
    },
    -2.61
     BRITAIN
    -2.61
     desember
    -2.58
     DÍA
    -2.56
     raven
    -2.55
    formatie
    -2.53
    ーズン
    -2.50
    POSITIVE LOGITS
     able
    3.30
     regarded
    3.05
     comprised
    2.92
     viewed
    2.70
     Roughly
    2.55
     Subsequently
    2.53
     Eventually
    2.52
     Ultimately
    2.50
     Specifically
    2.45
     Given
    2.44
    Activations Density 0.034%

    No Known Activations