© 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. 59692
    Prev
    Next
    INDEX
    Explanations

    mathematical expansion and simplification

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

    This neuron detects code‐style structural markers—especially curly braces ( `{` and `}` ), quotation marks, and comment delimiters—i.e. the punctuation of programming or JSON-like snippets.

    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
    “……
    -0.90
    ㅤㅤ
    -0.86
    koh
    -0.85
     kitab
    -0.81
     hvit
    -0.80
    ///<
    -0.80
     toch
    -0.80
    DRIVE
    -0.80
     знаю
    -0.79
    hamdulillah
    -0.79
    POSITIVE LOGITS
    `;
    1.08
    ----------------
    1.05
    end
    1.05
     fiabilidad
    1.05
     endregion
    1.03
    END
    1.02
     Kontrolle
    1.02
    ];
    1.02
    */
    0.98
    */
    
    0.96
    Activations Density 0.191%

    No Known Activations