© 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. 90631
    Prev
    Next
    INDEX
    Explanations

    detector parts

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

    The neuron is specialized to detect occurrences of the word “detector” (and its variants).

    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
    ᯅ
    -2.80
     姆
    -2.72
    倥
    -2.69
     underwhelming
    -2.58
    了一个
    -2.58
     futuristic
    -2.53
    埸
    -2.50
     ominous
    -2.48
     pinnacle
    -2.47
    𝐉
    -2.45
    POSITIVE LOGITS
     
    2.89
    部分が
    2.77
    <bos>
    2.75
     “
    2.69
    .
    2.58
    部分を
    2.55
      
    2.52
    狆
    2.52
    B
    2.50
    <i>
    2.48
    Activations Density 0.005%

    No Known Activations