© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113294
    Prev
    Next
    INDEX
    Explanations

    acronyms like CRP, PRC

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

    abbreviations for medical proteins and compounds, particularly CRP (C-reactive protein) and GRP (gene-related peptide).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on three-letter uppercase abbreviations (acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     好看
    -3.16
    盦
    -3.06
    ᯾
    -2.92
    焄
    -2.91
    </h2>
    -2.83
    
    -2.69
     办
    -2.69
    Ꭳ
    -2.63
    Ꮉ
    -2.63
    ୪
    -2.53
    POSITIVE LOGITS
    。"
    2.97
    al
    2.86
    '
    2.84
    u
    2.83
    \
    2.77
    ?"
    2.69
    "
    2.66
    ！"
    2.66
    *
    2.61
    on
    2.56
    Activations Density 0.009%

    No Known Activations