© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76210
    Prev
    Next
    INDEX
    Explanations

    Hello world

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

    The neuron is primarily triggered by numeric literals (digits and version numbers) 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
    chos
    -0.77
    дена
    -0.72
    phate
    -0.71
    Ϯ
    -0.71
    frutar
    -0.70
    Mori
    -0.70
    orte
    -0.69
     Resume
    -0.68
    hud
    -0.68
     Compose
    -0.67
    POSITIVE LOGITS
    Bisous
    0.75
    doped
    0.69
     determinación
    0.69
    𝚙
    0.69
     fld
    0.69
    тивной
    0.69
     Landschaft
    0.69
     mês
    0.69
     devido
    0.68
     吹
    0.68
    Activations Density 0.049%

    No Known Activations