© 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. 60429
    Prev
    Next
    INDEX
    Explanations

    immunological terms like IgA

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

    medical/scientific terms like "IgA" and brand names like "Ryanair" and "Air Fryer".

    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
    ↵
    -3.17
    7
    -2.77
    This
    -2.50
    3
    -2.30
    ;
    -2.27
    </b>
    -2.23
    es
    -2.19
    -2.17
    ו
    -2.13
    h
    -2.11
    POSITIVE LOGITS
     ͡°
    2.17
     dieß
    2.13
     pouvez
    2.05
    让他们
    1.98
    which
    1.96
    konto
    1.94
     serangan
    1.93
     hiciera
    1.93
     Перейти
    1.92
     condomínio
    1.90
    Activations Density 0.003%

    No Known Activations