© 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. 124072
    Prev
    Next
    INDEX
    Explanations

    voltage source, differential, or controlled

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

    The neuron strongly activates on the word “voltage,” identifying occurrences of that term (often part of “voltage‐gated” or similar).

    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
    埽
    -2.66
    媜
    -2.55
    之类的
    -2.52
    ቭ
    -2.47
    庒
    -2.47
    艄
    -2.45
    h
    -2.44
    Ꮵ
    -2.41
    {
    -2.39
    
    -2.39
    POSITIVE LOGITS
     of
    3.58
    .
    2.83
     $
    2.61
    ឵
    2.44
    杳
    2.38
    e
    2.28
     AND
    2.16
     следующих
    2.16
     обеспечение
    2.16
    ли
    2.14
    Activations Density 0.008%

    No Known Activations