© 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. 44313
    Prev
    Next
    INDEX
    Explanations

    pdf documents and biological terms

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

    proper names and technical terms, especially from fields like computing, medicine, and mythology.

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

    The neuron strongly fires on the literal token “Pdf.”

    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
    埽
    -3.06
    
    -2.80
    ة
    -2.66
    可以说
    -2.56
    鱨
    -2.50
    ς
    -2.48
    铼
    -2.48
     informar
    -2.48
    ⬯
    -2.45
    뿅
    -2.42
    POSITIVE LOGITS
    o
    3.83
    d
    3.41
     Quickly
    3.28
     Carefully
    3.23
     Beautifully
    3.09
     Primarily
    2.97
     Newly
    2.92
     Considered
    2.91
     
    2.91
    ...?
    2.89
    Activations Density 0.021%

    No Known Activations