© 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. 59925
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    The neuron is keyed to the “<” symbol that begins HTML/XML‐style tags (i.e. angle-bracketed markup).

    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
     polem
    -0.79
    わけで
    -0.78
     both
    -0.77
    쯤
    -0.77
     cuci
    -0.75
    录取
    -0.75
    父の
    -0.74
     Modes
    -0.74
    一張
    -0.74
    档案
    -0.73
    POSITIVE LOGITS
     entidades
    0.97
    thé
    0.89
    laying
    0.87
    郃
    0.87
    ditch
    0.86
    ifah
    0.85
    ntable
    0.85
     Sơn
    0.85
    ниш
    0.84
     öst
    0.81
    Activations Density 0.011%

    No Known Activations