© 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. 9405
    Prev
    Next
    INDEX
    Explanations

    biosensor, carousel, or product codes

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

    This neuron fires on HTML/XML tag tokens (e.g. “<code>,” “<pre>,” “<blockquote>,” “<big>”).

    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
    Figure
    -0.83
    preduce
    -0.81
     lucru
    -0.80
     подходя
    -0.80
    ніка
    -0.79
    I
    -0.79
     toán
    -0.79
    ]$
    -0.79
    CDD
    -0.78
    홋
    -0.76
    POSITIVE LOGITS
     vienen
    0.98
    diverse
    0.97
     kapsul
    0.94
    varying
    0.93
     سایر
    0.93
     soulign
    0.93
     считают
    0.89
     akrab
    0.87
    Zoro
    0.87
     tutur
    0.86
    Activations Density 0.001%

    No Known Activations