© 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. 1513
    Prev
    Next
    INDEX
    Explanations

    code and file headers

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

    This neuron detects tokens that are part of URLs or domain names (e.g. “http,” “www,” “.com”).

    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
    Elisa
    -0.85
    Emile
    -0.77
    пред
    -0.75
    咕
    -0.75
    💼
    -0.75
    |>
    -0.72
    hark
    -0.71
    Theres
    -0.71
    常规
    -0.71
     aperta
    -0.71
    POSITIVE LOGITS
     worsening
    0.84
    Hair
    0.81
    raman
    0.77
    moderator
    0.76
     journals
    0.76
    ̏
    0.75
     Ligne
    0.75
    undidad
    0.74
     muelle
    0.74
    ZZO
    0.73
    Activations Density 0.001%

    No Known Activations