© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34156
    Prev
    Next
    INDEX
    Explanations

    surgical procedures and treatments

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

    terms related to surgical procedures and operations in medical contexts.

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

    The neuron fires on mentions of “surgery” and its variants (e.g. “surgical”), i.e. references to operative procedures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    /
    -2.30
    下に
    -2.17
    泔
    -2.16
    “
    -2.13
    是这样
    -2.11
    ⟝
    -2.00
    当然是
    -1.96
    ⢓
    -1.93
    诶
    -1.93
    就直接
    -1.92
    POSITIVE LOGITS
    鉭
    2.50
    ↵
    2.44
    ۹
    2.38
     häufigsten
    2.28
    鹚
    2.22
     schlechte
    2.17
     Such
    2.16
     schmerz
    2.13
     Veränder
    2.08
    鎹
    2.06
    Activations Density 0.040%

    No Known Activations