© 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. 22-GEMMASCOPE-RES-131K
    7. 14419
    Prev
    Next
    INDEX
    Explanations

    specific scientific abbreviations and terms

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

    abbreviations and acronyms in scientific or technical 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_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
    ″]
    -0.94
    crania
    -0.89
     bagay
    -0.87
     liksom
    -0.86
    cademic
    -0.86
    ignment
    -0.85
    ieniem
    -0.85
    preneur
    -0.85
    initas
    -0.84
    Giá
    -0.83
    POSITIVE LOGITS
     Näch
    0.99
     плану
    0.96
    jusqu
    0.91
     in
    0.91
     of
    0.91
     useAppContext
    0.90
     Dacă
    0.88
    ឬ
    0.88
    utilité
    0.87
    Minden
    0.87
    Activations Density 0.246%

    No Known Activations