© 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. 128567
    Prev
    Next
    INDEX
    Explanations

    toxicology and antagonists

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

    words related to toxicology and pharmacology, such as "toxicological," "antagonist," and "toxicology".

    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
     télévisée
    -2.36
     indicato
    -2.33
     зді
    -2.22
    ená
    -2.14
     rád
    -2.14
     If
    -2.14
     pagare
    -2.11
    ۥ
    -2.09
     Kristus
    -2.09
    重要
    -2.09
    POSITIVE LOGITS
    s
    3.52
    ↵
    2.70
    im
    2.38
    am
    2.30
    k
    2.28
    you
    2.23
    m
    2.22
    <bos>
    2.20
    g
    2.19
    <i>
    2.16
    Activations Density 0.006%

    No Known Activations