© 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. 34-GEMMASCOPE-RES-131K
    7. 83434
    Prev
    Next
    INDEX
    Explanations

    scarring and wound healing

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

    medical terms related to scars, keloids, and skin conditions.

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

    The main thing this neuron does is detect mentions of scars and keloid-related terms (e.g., scar tissue, keloid, scar assessment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    رک
    -0.82
    礴
    -0.79
     bores
    -0.76
     Leaks
    -0.73
    leak
    -0.73
    usercontent
    -0.72
    Benedict
    -0.72
     rins
    -0.72
     leaks
    -0.72
    鎏
    -0.71
    POSITIVE LOGITS
     scar
    3.63
     scars
    3.27
    scar
    2.80
     Scar
    2.72
    Scar
    2.64
     scarring
    2.41
     Scars
    2.14
     scarred
    2.09
    scars
    2.08
     SCAR
    1.94
    Activations Density 0.038%

    No Known Activations