© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39817
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, or specific words

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

    The neuron fires on standalone numeric tokens (integers or decimals) that typically appear as metadata or measurements at the start of sections.

    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
     nowy
    -1.54
    身后的
    -1.43
     officiellement
    -1.41
     récemment
    -1.38
    ٪
    -1.35
     кото
    -1.29
     fréquemment
    -1.27
    ᵴ
    -1.27
    homonymie
    -1.26
    cesta
    -1.26
    POSITIVE LOGITS
     if
    1.70
    pography
    1.46
    pergillus
    1.45
     -
    1.36
    geddon
    1.33
    itons
    1.31
     ("
    1.27
     сзади
    1.27
    ampton
    1.27
    。“
    1.26
    Activations Density 0.048%

    No Known Activations