© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49375
    Prev
    Next
    INDEX
    Explanations

    single family home

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

    The neuron strongly activates on numeric tokens (digits, multi‐digit numbers, and related symbols like “$”), i.e. it detects numeric quantities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    彧
    -0.89
    carian
    -0.84
     could
    -0.80
     скорости
    -0.80
     acknowledged
    -0.78
     Römer
    -0.77
    残酷
    -0.77
    ethnicity
    -0.76
     แดง
    -0.75
    cías
    -0.74
    POSITIVE LOGITS
    プログラム
    0.88
    Sales
    0.83
    全球
    0.81
    营销
    0.78
     THOR
    0.77
     pieds
    0.77
    loh
    0.76
    inhard
    0.74
    Residential
    0.74
    нений
    0.73
    Activations Density 0.020%

    No Known Activations