© 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. 67513
    Prev
    Next
    INDEX
    Explanations

    future medical conditions and political events

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

    specific medical conditions and anatomical terms in healthcare contexts.

    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
    Adam
    -0.79
    setzen
    -0.77
    𝐣
    -0.75
    ☾
    -0.73
    ẫy
    -0.72
    anak
    -0.71
    Analog
    -0.70
    comprar
    -0.70
     fijne
    -0.69
     suced
    -0.69
    POSITIVE LOGITS
     future
    1.84
     pending
    1.45
    将来
    1.41
    future
    1.35
     preparing
    1.34
     upcoming
    1.30
     potential
    1.30
     preparation
    1.28
     someday
    1.28
     preparations
    1.27
    Activations Density 0.180%

    No Known Activations