© 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. 99414
    Prev
    Next
    INDEX
    Explanations

    It is followed by description

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

    The main thing this neuron does is detect occurrences of the copular verb “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
    1
    -3.53
    8
    -3.50
    7
    -3.38
    9
    -3.19
    the
    -3.03
    4
    -2.98
    3
    -2.95
    5
    -2.92
    2
    -2.80
    6
    -2.69
    POSITIVE LOGITS
     Which
    3.25
     It
    2.44
     a
    2.42
     entendi
    2.41
     What
    2.41
     condenado
    2.27
     interpreta
    2.20
     now
    2.20
     There
    2.19
    だった
    2.14
    Activations Density 0.807%

    No Known Activations