© 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. 131050
    Prev
    Next
    INDEX
    Explanations

    medical and legal prefixes

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

    medical and scientific field names or specialties like Geriatric, Opioid, Mental Health, and Schizophrenia.

    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
     ندارم
    -1.27
     you
    -1.26
     turun
    -1.23
     пище
    -1.21
    FFECT
    -1.20
     didik
    -1.18
     reban
    -1.17
     terle
    -1.16
     celta
    -1.16
     teritor
    -1.16
    POSITIVE LOGITS
    ;
    1.35
     '
    1.33
    related
    1.30
    -
    1.17
    ,
    1.14
    assemblée
    1.08
    ৯
    1.07
    _
    1.05
     Then
    1.05
    mathbf
    1.05
    Activations Density 0.059%

    No Known Activations