© 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. 10-GEMMASCOPE-RES-131K
    4. 10336
    Prev
    Next
    INDEX
    Explanations

    pm and ± symbols

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

    The neuron detects occurrences of the “±” (pm) symbol used to denote uncertainties or plus-minus values.

    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
    GRAFIA
    -2.55
     устройств
    -2.28
    ୩
    -2.28
    ՙ
    -2.28
    ichteten
    -2.27
    erschrank
    -2.22
    ፁ
    -2.19
     membantu
    -2.14
    '||
    -2.11
    irsty
    -2.08
    POSITIVE LOGITS
    $
    2.56
    while
    2.44
    *
    2.25
    鹛
    2.13
    when
    2.11
     marginally
    2.11
     一个
    1.98
     puzzling
    1.96
    but
    1.95
     copious
    1.95
    Activations Density 0.001%

    No Known Activations