© 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. 34-GEMMASCOPE-RES-131K
    7. 47662
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and commas

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

    The neuron is specialized for spotting document metadata elements—particularly all-caps headings, docket numbers, dates, and similar structured tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Vídeo
    -0.98
    Sushi
    -0.94
    дию
    -0.91
     anfangen
    -0.86
    tarta
    -0.86
    sushi
    -0.85
    Mí
    -0.85
    豸
    -0.84
    orderid
    -0.83
     myös
    -0.82
    POSITIVE LOGITS
     ):
    1.46
     );
    1.22
     ).
    1.20
     ),
    1.16
     ,
    1.13
     ,"
    1.09
     는
    1.03
     ,
    1.02
     "];
    0.98
     )
    0.96
    Activations Density 0.007%

    No Known Activations