© 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. 22-GEMMASCOPE-RES-131K
    4. 9464
    Prev
    Next
    INDEX
    Explanations

    comparisons with 'than' or 'чем'

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

    The neuron fires whenever it sees numeric tokens (digits) – it’s basically a “number‐finder” neuron.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.19
     embrague
    -1.08
     about
    -1.04
     like
    -1.01
     I
    -0.99
     ingeniero
    -0.98
    Ingredienti
    -0.94
     only
    -0.93
    பெ
    -0.92
    DJANGO
    -0.88
    POSITIVE LOGITS
     venda
    1.03
     rosse
    0.97
    others
    0.97
     others
    0.93
     カーディガン
    0.91
    uVar
    0.90
     africaine
    0.89
     сама
    0.87
     lança
    0.86
    rasında
    0.86
    Activations Density 0.052%

    No Known Activations