© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21268
    Prev
    Next
    INDEX
    Explanations

    medical and scientific studies

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

    The neuron activates on the equals sign (=) in academic citations and statistical notations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -2.38
    .
    -2.36
    Also
    -2.11
    when
    -2.05
    It
    -2.03
    Just
    -2.02
    9
    -2.02
    There
    -2.02
    3
    -2.02
    An
    -1.99
    POSITIVE LOGITS
    を使用した
    1.99
    ⩤
    1.97
     construite
    1.85
    鰾
    1.81
    
    1.80
     chô
    1.77
    ⸗
    1.77
     Jednak
    1.77
     gestión
    1.75
    锱
    1.73
    Activations Density 0.014%

    No Known Activations