© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74098
    Prev
    Next
    INDEX
    Explanations

    medical relapse

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

    The neuron detects medical or clinical terms related to disease relapse or recurrence.

    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
    </h3>
    -2.78
     You
    -2.22
     terrific
    -2.06
    ro
    -2.02
     Your
    -1.97
     ensuing
    -1.92
    氿
    -1.89
    ين
    -1.84
     fabulous
    -1.84
    ING
    -1.83
    POSITIVE LOGITS
    咘
    2.08
    𖡼
    2.08
    ↵
    2.02
     anglers
    1.98
    s
    1.83
    Rumble
    1.79
     Providing
    1.79
    uudet
    1.78
     longstanding
    1.72
    牁
    1.70
    Activations Density 0.026%

    No Known Activations