© 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. 34-GEMMASCOPE-RES-131K
    7. 38308
    Prev
    Next
    INDEX
    Explanations

    equivalent

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

    The neuron activates on numeric expressions—digits, quantities, and associated units or magnitudes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    imanapun
    -1.00
     diferentes
    -0.90
    特に
    -0.90
    cader
    -0.87
     fórmula
    -0.85
     хотела
    -0.84
    gernaut
    -0.82
    ingabe
    -0.81
     minimal
    -0.81
     особенно
    -0.81
    POSITIVE LOGITS
     equivalent
    2.02
    equivalent
    1.70
    Equivalent
    1.69
     entire
    1.60
     Equivalent
    1.50
     equivale
    1.39
    équi
    1.39
     équi
    1.30
     equivalente
    1.30
     yearly
    1.24
    Activations Density 0.031%

    No Known Activations