© 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. 67841
    Prev
    Next
    INDEX
    Explanations

    caused by

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

    The neuron identifies causal relationships where something is "caused by" something else, particularly in medical and scientific contexts.

    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
     vada
    -2.00
    時には
    -2.00
     italia
    -1.80
     bluse
    -1.73
     сцен
    -1.73
     valentino
    -1.72
     dacia
    -1.71
    覿
    -1.70
    ｛
    -1.66
     stund
    -1.65
    POSITIVE LOGITS
     természetes
    1.88
     These
    1.84
     között
    1.73
     teljesen
    1.68
     трёх
    1.66
    ↵
    1.66
     maximise
    1.65
     oluşan
    1.63
     The
    1.61
    ходят
    1.60
    Activations Density 0.043%

    No Known Activations