© 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. 94003
    Prev
    Next
    INDEX
    Explanations

    internet addresses and web links

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

    The neuron detects URL patterns, especially “http://” and related link tokens.

    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
    ènement
    -1.06
    日閲覧
    -1.05
    authentication
    -1.00
    astricht
    -1.00
     Jahre
    -1.00
    Та
    -0.98
    太郎
    -0.98
    autoreleasepool
    -0.96
    است
    -0.96
     الله
    -0.95
    POSITIVE LOGITS
    ://
    1.17
     verschil
    1.16
     играет
    1.13
    橚
    1.07
    であるが
    1.05
     zwi
    1.05
     erreich
    1.05
    toi
    1.05
     betekent
    1.04
     LMAO
    1.04
    Activations Density 0.044%

    No Known Activations