© 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. 22-GEMMASCOPE-RES-131K
    7. 15667
    Prev
    Next
    INDEX
    Explanations

    neoplasms, firearms, intercourse, lipids, aviators, handbags

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

    words related to medical and scientific terminology, particularly disease conditions and anatomical terms.

    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
    5
    -1.40
    8
    -1.20
    2
    -1.20
     misericordia
    -1.18
    7
    -1.17
    徐々に
    -1.14
     felpa
    -1.13
     تغییر
    -1.13
    efter
    -1.13
    還能
    -1.11
    POSITIVE LOGITS
    小伙伴
    1.34
    大佬
    1.32
     kā
    1.31
     stanovnika
    1.26
     bevor
    1.23
    держание
    1.20
    хоро
    1.20
    ında
    1.16
    GIUM
    1.16
    iembre
    1.14
    Activations Density 0.238%

    No Known Activations