© 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. 10-GEMMASCOPE-RES-131K
    7. 41725
    Prev
    Next
    INDEX
    Explanations

    http urls

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

    The neuron fires on URL protocol prefixes, specifically the “http://” sequence.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -3.05
    and
    -2.66
    </h2>
    -2.58
    っていう
    -2.25
    _
    -2.16
    It
    -2.11
    кий
    -2.09
    言えば
    -2.09
     If
    -2.06
    结语
    -2.06
    POSITIVE LOGITS
    좆
    2.83
     erwähnten
    2.78
    
    2.48
     mengumumkan
    2.44
     ,‬
    2.38
     mauva
    2.36
    慙
    2.31
     \
    2.28
     genannten
    2.27
     sélections
    2.25
    Activations Density 0.066%

    No Known Activations