© 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. 22-GEMMASCOPE-RES-131K
    7. 27922
    Prev
    Next
    INDEX
    Explanations

    Anniversary Gifts

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

    The neuron is detecting standalone numeric constants (numbers).

    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
     by
    -0.95
    izacion
    -0.94
     додат
    -0.93
     rodas
    -0.91
     that
    -0.91
     informar
    -0.91
    ету
    -0.89
     parha
    -0.88
     dú
    -0.87
    iempos
    -0.87
    POSITIVE LOGITS
    ฑ
    1.02
    ͧ
    1.00
     unterstüt
    0.99
    することができます
    0.99
    还能
    0.98
     hamsters
    0.97
     operativos
    0.95
     时
    0.93
    给你
    0.92
     ווע
    0.91
    Activations Density 0.013%

    No Known Activations