© 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. 13153
    Prev
    Next
    INDEX
    Explanations

    diseases and their causative agents

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

    disease-causing pathogens like bacteria, viruses, and other microorganisms.

    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
    皈
    -1.32
    篆
    -1.28
     eſt
    -1.26
     mendatang
    -1.26
    ſe
    -1.21
    neous
    -1.20
     ſi
    -1.19
     things
    -1.17
    小镇
    -1.17
     eorum
    -1.16
    POSITIVE LOGITS
     terrorismo
    1.53
    简约
    1.46
    以上です
    1.38
    capable
    1.35
    ába
    1.34
     cucchiai
    1.34
    我們的
    1.31
    Karakter
    1.30
    媽媽
    1.28
    つづく
    1.27
    Activations Density 0.231%

    No Known Activations