© 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. 22-GEMMASCOPE-RES-131K
    7. 9713
    Prev
    Next
    INDEX
    Explanations

    Q: questions or starting with "The" or "Per"

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

    This neuron responds to HTML markup, particularly the opening of tags (the “<tag …>” syntax) and their attributes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    gunakan
    -1.16
     varier
    -1.08
    єн
    -1.03
    tım
    -1.00
    beschreibung
    -1.00
     pratos
    -1.00
     hemd
    -0.97
    vraag
    -0.97
     poži
    -0.97
     nabi
    -0.95
    POSITIVE LOGITS
    R
    0.93
     R
    0.91
    w
    0.86
    my
    0.85
    L
    0.84
    ry
    0.84
    合唱
    0.83
     my
    0.83
    par
    0.83
     L
    0.82
    Activations Density 0.003%

    No Known Activations