© 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. 21895
    Prev
    Next
    INDEX
    Explanations

    nanoscale and microscale

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

    The neuron detects the word "nanoscale" and related scientific scale terminology.

    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
    鏷
    -2.63
    }
    -2.61
    咵
    -2.52
     militares
    -2.38
    
    -2.36
    隂
    -2.30
    嘚
    -2.27
    甚麼
    -2.27
     Infór
    -2.25
     decim
    -2.20
    POSITIVE LOGITS
    just
    2.59
    (
    2.58
    你在
    2.47
    i
    2.44
    ка
    2.42
    cale
    2.39
    ньому
    2.31
    “
    2.16
    ſelves
    2.11
    しました
    2.03
    Activations Density 0.012%

    No Known Activations