© 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. 11581
    Prev
    Next
    INDEX
    Explanations

    ablation procedure

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

    The neuron detects medical procedures related to ablation, particularly in the context of surgical or therapeutic tissue removal.

    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
    鐃
    -2.59
    ar
    -2.41
    みる
    -2.30
     him
    -2.27
    čů
    -2.23
    猻
    -2.22
    𖥧
    -2.19
    𝄆
    -2.19
    }$
    -2.17
    没有了
    -2.16
    POSITIVE LOGITS
    ↵
    4.66
    ;
    2.17
    i
    2.13
    ⢕
    2.05
    -
    2.02
     critically
    1.87
    $
    1.87
     یکی
    1.86
    龃
    1.84
     afford
    1.79
    Activations Density 0.012%

    No Known Activations