© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47342
    Prev
    Next
    INDEX
    Explanations

    evidence and citations

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

    The neuron is detecting web URLs (i.e. domain names and protocol parts like “http://www…org/…”) in the text.

    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
    球
    -0.70
     wh
    -0.68
     nhận
    -0.65
    ⣦
    -0.65
    okhttp
    -0.64
    pytorch
    -0.63
     unlock
    -0.63
    禍
    -0.63
     should
    -0.62
    ською
    -0.61
    POSITIVE LOGITS
    Evidence
    1.02
     term
    0.94
     evidence
    0.93
    Term
    0.90
     Evidence
    0.88
    нс
    0.87
    evidence
    0.86
    证据
    0.85
    Referanser
    0.85
     curator
    0.83
    Activations Density 0.028%

    No Known Activations