© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44820
    Prev
    Next
    INDEX
    Explanations

    closing html tags

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

    The neuron flags numeric literals (e.g. attribute values, percentages, dimensions) appearing in HTML/XML tags.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -2.42
    ]
    -1.84
    }
    -1.79
    ↵
    -1.77
                  
    -1.66
    >
    -1.66
            
    -1.61
     Shouldn
    -1.60
                 
    -1.55
    Any
    -1.54
    POSITIVE LOGITS
    寕
    1.80
     embarazada
    1.66
     médaille
    1.62
    ໑
    1.59
     they
    1.53
    鸩
    1.52
    mejores
    1.49
     was
    1.48
    antaranya
    1.48
    sistencia
    1.46
    Activations Density 0.014%

    No Known Activations