© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104220
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and exponents

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

    The neuron activates on occurrences of the “sqrt” token (i.e. square‐root expressions).

    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
    ╚
    -0.88
    药品
    -0.85
    ก่อน
    -0.82
     letzten
    -0.80
    databases
    -0.79
     yake
    -0.78
     hotels
    -0.77
    Job
    -0.77
     job
    -0.77
    副
    -0.77
    POSITIVE LOGITS
     acompan
    1.14
     ocasion
    1.03
    breviated
    1.02
     nuevos
    0.99
     antici
    0.95
     asume
    0.95
     כד
    0.94
     ModelExpression
    0.94
     conduce
    0.93
    katkan
    0.92
    Activations Density 0.092%

    No Known Activations