© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44654
    Prev
    Next
    INDEX
    Explanations

    plague disease or other afflictions

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

    mentions of the word "plague" in text.

    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
    ۔
    -2.95
     内装
    -2.61
    𓍯
    -2.56
    ፨
    -2.56
    鸲
    -2.55
    熥
    -2.53
    甍
    -2.33
    ção
    -2.25
    ⛩
    -2.23
    윔
    -2.23
    POSITIVE LOGITS
     of
    3.67
    ↵
    3.20
    y
    2.66
    </b>
    2.36
    other
    2.27
     To
    2.25
     otras
    2.25
    );
    2.17
    ("
    2.06
    人也
    2.06
    Activations Density 0.002%

    No Known Activations