© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30480
    Prev
    Next
    INDEX
    Explanations

    website sections and news sources

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

    This neuron detects web‐address-like tokens—i.e. components of URLs or domain names (e.g. “.com,” “.net,” slashes, and similar markers).

    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
     Datenschutzer
    -0.98
     либо
    -0.88
     З
    -0.88
     either
    -0.86
     буквы
    -0.86
     olvid
    -0.82
    ის
    -0.82
     Как
    -0.78
     zarówno
    -0.78
     vooral
    -0.78
    POSITIVE LOGITS
    <eos>
    1.48
    ).\\
    1.09
    ovala
    1.07
    .”)
    1.07
     with
    1.05
     Editing
    1.05
    お部屋
    1.05
    úan
    1.05
     Gorb
    1.05
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.02
    Activations Density 0.007%

    No Known Activations