© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75469
    Prev
    Next
    INDEX
    Explanations

    glioblastoma, gliomas, glial

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

    The neuron detects the term "Gli" particularly when it appears in medical/scientific contexts related to glioblastoma, glial cells, and brain tissue.

    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
    </b>
    -2.75
    鐠
    -2.64
    ༑
    -2.64
    紲
    -2.61
    我先
    -2.61
    </sup>
    -2.56
    艫
    -2.53
    醅
    -2.41
    岜
    -2.33
    ⤙
    -2.31
    POSITIVE LOGITS
    "
    4.13
    }
    3.30
     ‚
    3.00
    {
    2.94
     This
    2.80
    *
    2.64
    ?"
    2.59
    ’
    2.59
    ."
    2.59
    ,"
    2.58
    Activations Density 0.003%

    No Known Activations