© 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. 22-GEMMASCOPE-RES-131K
    7. 28301
    Prev
    Next
    INDEX
    Explanations

    spheres, circles, circumference, grid, surrounding

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

    The neuron activates on numerals and numeric expressions (e.g. integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     belang
    -1.08
     different
    -1.06
    vantaged
    -1.02
    他
    -0.96
    ৭
    -0.96
     morgen
    -0.96
     différent
    -0.94
    พาะ
    -0.93
     heilig
    -0.93
     system
    -0.93
    POSITIVE LOGITS
     inicios
    1.02
    ρας
    1.00
    ὺς
    0.97
     bosques
    0.96
    èmes
    0.96
     miembros
    0.93
     comienzos
    0.93
     empez
    0.92
     سبتمبر
    0.92
     chrétienne
    0.92
    Activations Density 0.051%

    No Known Activations