© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12266
    Prev
    Next
    INDEX
    Explanations

    table formatting

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

    The neuron fires on numeric tokens in table‐like structures (e.g. the column “Required 644” or the width markers in ASCII/markdown tables), so it’s detecting numbers that define table formatting or column metadata.

    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
     to
    -0.95
     Set
    -0.83
    )*(
    -0.82
     at
    -0.82
     You
    -0.82
    roir
    -0.81
    ържа
    -0.80
    嫉妒
    -0.80
     various
    -0.79
    ϫ
    -0.78
    POSITIVE LOGITS
    |}
    1.66
     puentes
    1.01
    ']
    1.00
    ,]
    0.99
    \}
    0.99
    equip
    0.97
    
    0.96
    .}
    0.95
    Responsibilities
    0.94
    </tr>
    0.94
    Activations Density 0.004%

    No Known Activations