© 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. 123464
    Prev
    Next
    INDEX
    Explanations

    state of being

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

    The neuron fires on the standalone copula “is.”

    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
    the
    -3.67
    1
    -3.64
    a
    -3.30
    7
    -3.27
    6
    -3.03
    2
    -2.94
    ⩩
    -2.91
    ,"
    -2.84
    4
    -2.84
    8
    -2.78
    POSITIVE LOGITS
     Which
    3.56
     We
    2.81
    眨眼
    2.72
     not
    2.70
     During
    2.44
     detecta
    2.38
    錚
    2.34
     now
    2.31
     interpreta
    2.31
     is
    2.30
    Activations Density 0.850%

    No Known Activations