© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81619
    Prev
    Next
    INDEX
    Explanations

    action or inaction

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

    This neuron activates on HTML/XML markup syntax (tags, attributes, and their delimiters).

    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
    ˠ
    -0.81
    الش
    -0.79
    eters
    -0.79
    龈
    -0.78
     Playboy
    -0.77
    tructor
    -0.77
    ázquez
    -0.75
    chitis
    -0.75
     issu
    -0.75
     Anlagen
    -0.75
    POSITIVE LOGITS
    ッコ
    0.91
    ActionTypes
    0.88
     inaction
    0.87
     action
    0.84
    lettes
    0.82
     Action
    0.80
     COSTS
    0.79
    !/
    0.79
    ActionType
    0.75
    xbd
    0.74
    Activations Density 0.046%

    No Known Activations