© 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. 34-GEMMASCOPE-RES-131K
    4. 2061
    Prev
    Next
    INDEX
    Explanations

    numpy array generation

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

    The neuron fires on numeric literals (digits) in code.

    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
    Fight
    -0.74
    Bris
    -0.71
    Carcinogenicity
    -0.68
    캐
    -0.68
     JOSÉ
    -0.68
    luss
    -0.68
     defStyleAttr
    -0.66
     wohn
    -0.65
     kalimat
    -0.65
    judul
    -0.65
    POSITIVE LOGITS
     random
    2.83
    random
    2.55
     randomly
    2.25
     rand
    2.22
    rand
    2.11
    随机
    2.08
    randn
    2.05
     Random
    1.98
    Random
    1.95
     randomized
    1.82
    Activations Density 0.028%

    No Known Activations