© 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. 66003
    Prev
    Next
    INDEX
    Explanations

    end of code or markup

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

    The neuron fires on mathematical notation—particularly digits, formula tokens, and equation punctuation.

    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
     kurzer
    -1.01
     polícia
    -0.95
    omore
    -0.94
    ったのは
    -0.92
    .
    
    -0.90
    鄙
    -0.89
     imprensa
    -0.88
    ryd
    -0.88
    Ȧ
    -0.88
    uha
    -0.87
    POSITIVE LOGITS
    </blockquote>
    4.09
    </h2>
    2.44
    </td>
    2.23
    */
    2.19
    ```
    2.06
    </code>
    2.05
     */
    2.03
    ");
    2.00
    </h6>
    1.98
    </tbody>
    1.86
    Activations Density 0.024%

    No Known Activations