© 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. 22-GEMMASCOPE-RES-131K
    7. 27173
    Prev
    Next
    INDEX
    Explanations

    finding a cure

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

    the word "cure" and phrases related to medical treatments for diseases or conditions.

    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_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
     he
    -2.70
    铊
    -2.38
    ৢ
    -2.33
    苙
    -2.33
    ⏑
    -2.25
     You
    -2.23
    🗹
    -2.14
     своем
    -2.14
    皞
    -2.14
     So
    -2.03
    POSITIVE LOGITS
    ៚
    2.20
    鄖
    2.11
    Also
    2.09
     букет
    2.02
     pikir
    1.98
     veterinario
    1.94
    They
    1.93
     будешь
    1.92
     フ
    1.89
     terremoto
    1.86
    Activations Density 0.008%

    No Known Activations