© 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. 10-GEMMASCOPE-RES-131K
    7. 41744
    Prev
    Next
    INDEX
    Explanations

    `~` and `approx`

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

    The neuron fires on the LaTeX “\sim” (and related tilde‐style) tokens used to denote similarity or distribution (e.g. X \sim N, i.i.d.) in math contexts.

    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
    ilización
    -2.08
    姈
    -2.06
    gucig
    -2.00
    茕
    -1.95
    ztő
    -1.84
    
    -1.84
    醅
    -1.82
    ACHUSET
    -1.78
    苌
    -1.76
    ᭝
    -1.75
    POSITIVE LOGITS
     -
    2.17
    “
    1.90
    典型的
    1.77
    にします
    1.74
     effectively
    1.70
     decisively
    1.67
    ar
    1.67
     ought
    1.61
     suspected
    1.61
    再来
    1.60
    Activations Density 0.005%

    No Known Activations