© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66001
    Prev
    Next
    INDEX
    Explanations

    translational research and science

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

    The neuron detects forms of the word "translational" in scientific and medical 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
    How
    -2.75
     By
    -2.73
    Our
    -2.66
    Each
    -2.64
     détaillée
    -2.63
    Why
    -2.52
    What
    -2.47
    摇了
    -2.44
    Additionally
    -2.41
    These
    -2.39
    POSITIVE LOGITS
    '
    2.97
     nėra
    2.19
    ቍ
    2.11
     incluidos
    2.06
     aseg
    2.03
     espèce
    2.02
     boste
    1.98
    ⢓
    1.93
     valsty
    1.92
     feine
    1.91
    Activations Density 0.004%

    No Known Activations