© 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. 13144
    Prev
    Next
    INDEX
    Explanations

    a/an/the followed by a noun

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

    The neuron flags mentions of specific research tools, instruments, software packages, and commercial assay kits in methods sections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     óptica
    -1.64
    ejemplo
    -1.48
    prueba
    -1.48
    
    -1.45
     якщо
    -1.42
     dovuto
    -1.38
    abilirsiniz
    -1.38
    Trọng
    -1.35
     adatta
    -1.34
    bolsa
    -1.32
    POSITIVE LOGITS
     all
    1.81
     by
    1.71
     both
    1.46
     nasional
    1.43
     velours
    1.28
     pribadi
    1.27
    '
    1.27
     and
    1.27
     housse
    1.21
     informée
    1.21
    Activations Density 0.181%

    No Known Activations