© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65190
    Prev
    Next
    INDEX
    Explanations

    gated ion channels

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

    terms referring to voltage-gated ion channels or related structures in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on occurrences of the substring “gated,” i.e. words ending in “gated.”

    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
    1
    -2.45
    .
    -2.02
     niemand
    -1.95
    很是
    -1.82
     ajouter
    -1.75
    s
    -1.74
    在自己
    -1.72
     dagli
    -1.72
     Officially
    -1.72
     dobbiamo
    -1.71
    POSITIVE LOGITS
    ("
    2.17
    ⑊
    2.13
    /"
    2.11
    臜
    2.11
    沕
    2.09
     of
    2.06
     início
    2.06
    /,
    2.00
    \_
    1.98
    냑
    1.98
    Activations Density 0.004%

    No Known Activations