© 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. 55682
    Prev
    Next
    INDEX
    Explanations

    legal or license text

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

    The neuron strongly activates on non‐lexical, high‐information tokens—things like punctuation marks, digits, and formatting tags—i.e. structured metadata or markup elements rather than ordinary words.

    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
    romeda
    -1.09
     matic
    -1.06
     serio
    -1.06
     parís
    -1.05
    therosclerosis
    -1.05
     ftate
    -1.02
    wwwww
    -1.02
    olesale
    -0.99
     coser
    -0.99
    🐊
    -0.99
    POSITIVE LOGITS
     end
    0.95
    ...
    0.91
     stimmen
    0.88
     rest
    0.85
     list
    0.84
    e
    0.83
    ist
    0.82
     tr
    0.80
     ch
    0.80
     vocal
    0.79
    Activations Density 0.005%

    No Known Activations