© 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. 101294
    Prev
    Next
    INDEX
    Explanations

    neuronal cell states and functions

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

    The neuron activates for the word "neuronal" and related terms in neuroscience 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
     itſelf
    -3.14
    镦
    -3.09
    峩
    -2.94
    屙
    -2.88
    躝
    -2.84
     gewi
    -2.83
    捽
    -2.77
    耵
    -2.75
    s
    -2.66
    㩒
    -2.64
    POSITIVE LOGITS
     That
    3.25
     After
    2.95
     Much
    2.86
    ↵
    2.72
     Like
    2.55
    大量的
    2.53
     Until
    2.48
     Completely
    2.48
    section
    2.45
     や
    2.45
    Activations Density 0.005%

    No Known Activations