© 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. 10-GEMMASCOPE-RES-131K
    7. 90786
    Prev
    Next
    INDEX
    Explanations

    prokinetic agent, secretagogue, venotonic compounds

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

    pharmaceutical drug names in scientific/medical literature.

    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
     hinders
    -1.23
     многих
    -1.23
    猜测
    -1.18
     misschien
    -1.16
     Who
    -1.15
    noid
    -1.15
     других
    -1.14
    esss
    -1.14
     applies
    -1.14
     agrees
    -1.13
    POSITIVE LOGITS
    Angebot
    1.34
    小行星
    1.33
    躂
    1.32
    Detta
    1.29
    lastung
    1.27
    Varför
    1.25
    Lịch
    1.21
    nicht
    1.20
    Hilfe
    1.20
    enzial
    1.20
    Activations Density 0.260%

    No Known Activations