© 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. 89778
    Prev
    Next
    INDEX
    Explanations

    comment markers and endings

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

    This neuron fires on code‐ or markup-style tokens—identifiers, numeric literals, comment-heading markers, and other technical/structural words rather than ordinary prose.

    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
     by
    -0.97
    °)
    -0.94
     also
    -0.91
     in
    -0.90
     polícia
    -0.88
    mozilla
    -0.88
    **
    
    -0.87
     платья
    -0.86
     with
    -0.86
     pemeriksaan
    -0.85
    POSITIVE LOGITS
    </blockquote>
    1.91
    </h2>
    1.09
     });
    1.05
    ilirsiniz
    1.04
     beſt
    1.03
    `);
    1.02
    ἄ
    0.98
    σιο
    0.96
    ```
    0.95
     positiva
    0.94
    Activations Density 0.001%

    No Known Activations