© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13525
    Prev
    Next
    INDEX
    Explanations

    statistical variance

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

    The neuron activates on occurrences of the word “variance” (or “variances”) in a statistical or scientific context.

    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
    埽
    -3.67
    莇
    -3.64
    㩒
    -3.14
     Inſ
    -3.13
    僂
    -3.00
    茈
    -2.98
    宬
    -2.97
    闥
    -2.94
    庒
    -2.88
     撮っ
    -2.86
    POSITIVE LOGITS
    e
    3.78
    V
    3.11
    ↵
    2.97
    X
    2.97
    U
    2.89
    Y
    2.86
    ?
    2.75
    L
    2.69
    S
    2.67
    T
    2.67
    Activations Density 0.003%

    No Known Activations