© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108620
    Prev
    Next
    INDEX
    Explanations

    HTML class names and tags

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

    The neuron fires on hyphenated identifier tokens—particularly CSS class‐ or ID‐style names and similarly formatted HTML attribute strings.

    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
     Olympedia
    -1.04
    윤
    -0.91
    ویژگی
    -0.90
    نحوه
    -0.90
    ادامه
    -0.88
    lées
    -0.88
     диски
    -0.87
    酶
    -0.85
    امکان
    -0.84
    بررسی
    -0.84
    POSITIVE LOGITS
     DEMO
    0.91
     lel
    0.90
     portatil
    0.83
    铝
    0.82
     »>
    0.82
    toys
    0.81
    developmental
    0.81
    drops
    0.80
     %).
    0.79
     granite
    0.79
    Activations Density 0.015%

    No Known Activations