© 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. 73824
    Prev
    Next
    INDEX
    Explanations

    equal to a measure or quality

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

    The neuron reliably fires on the standalone word “equal.”

    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
     of
    -3.58
     Now
    -1.95
     From
    -1.90
    .
    -1.78
     The
    -1.70
    de
    -1.70
     Unfortunately
    -1.66
     Subsequently
    -1.66
     Instead
    -1.65
     maupun
    -1.65
    POSITIVE LOGITS
    sistence
    1.88
    vaders
    1.84
     resistentes
    1.80
    volved
    1.80
    haled
    1.80
    junctive
    1.74
    volvement
    1.73
    viato
    1.72
    continence
    1.70
    ositol
    1.67
    Activations Density 0.014%

    No Known Activations