© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15815
    Prev
    Next
    INDEX
    Explanations

    less common

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

    The neuron detects comparative quantifier phrases—especially the word “less” (often in “less than X”) indicating a small quantity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Torpedo
    0.69
     शॉर्ट
    0.67
    кра
    0.65
    요
    0.64
     отсутствии
    0.63
    اله
    0.62
    underset
    0.62
    シェア
    0.62
    इससे
    0.62
    वृ
    0.61
    POSITIVE LOGITS
     fortunate
    1.13
     $(<
    1.05
     Less
    1.00
    ened
    0.96
    ening
    0.92
    (<
    0.86
    Less
    0.86
     (<
    0.83
    -<
    0.82
    fortunate
    0.77
    Activations Density 0.193%

    No Known Activations