© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48860
    Prev
    Next
    INDEX
    Explanations

    next steps

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

    This neuron detects the boundaries of XML tags (e.g. the “<”, tag names like “string” or “item”, and “</…>” markers).

    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
    substack
    -0.81
     Meilleur
    -0.78
    惘
    -0.76
    кори
    -0.76
     cocina
    -0.75
     спро
    -0.75
    Кры
    -0.72
    至尊
    -0.72
    ῾
    -0.71
    //$
    -0.71
    POSITIVE LOGITS
     '.';
    0.85
     []);
    0.84
    ];
    0.84
     overly
    0.78
     allerdings
    0.76
    助
    0.76
     najbolj
    0.75
    .")]
    0.75
     jedoch
    0.75
     могут
    0.75
    Activations Density 0.001%

    No Known Activations