© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10948
    Prev
    Next
    INDEX
    Explanations

    risperidone, risers, Risser

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

    the letters "ris" in medical, technical, or proper name contexts.

    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
    5
    -2.97
    \
    -2.92
    t
    -2.69
    ↵
    -2.59
    In
    -2.59
    とっても
    -2.58
    ↵↵
    -2.55
    the
    -2.53
    a
    -2.50
    2
    -2.47
    POSITIVE LOGITS
    ⃙
    2.59
    龃
    2.53
    ris
    2.48
    镦
    2.42
    
    2.39
    AdvEx
    2.36
    RIS
    2.31
    螄
    2.23
     likewise
    2.23
     cele
    2.23
    Activations Density 0.002%

    No Known Activations