© 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. 22-GEMMASCOPE-RES-131K
    7. 84365
    Prev
    Next
    INDEX
    Explanations

    differential diagnosis

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

    medical conditions being compared or differentiated from other diagnoses.

    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
     sentimentos
    -0.85
     inox
    -0.84
     nuoc
    -0.82
    ẽ
    -0.80
     pensamentos
    -0.79
    カチ
    -0.79
     curie
    -0.78
    镜子
    -0.78
     niedersachsen
    -0.76
     ASCII
    -0.75
    POSITIVE LOGITS
     вместо
    1.28
     instead
    1.12
     simplemente
    1.04
    ではなく
    1.00
    真正
    0.99
     Instead
    0.93
     just
    0.92
    แค่
    0.91
    instead
    0.90
     caused
    0.90
    Activations Density 0.114%

    No Known Activations