© 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. 22-GEMMASCOPE-RES-131K
    7. 35323
    Prev
    Next
    INDEX
    Explanations

    URLs with file extensions

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

    The neuron specializes in detecting URL fragments—domain names, path slashes, dots, file extensions, and numeric identifiers in web addresses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     not
    -1.22
     Olympedia
    -1.14
     your
    -1.14
     nothing
    -1.12
    itzende
    -1.10
    ughter
    -1.07
    cómo
    -1.05
     voorwaarden
    -1.05
     for
    -1.04
    Réalisation
    -1.04
    POSITIVE LOGITS
    ay
    1.30
    g
    1.27
    参考にして
    1.19
    mised
    1.16
    k
    1.14
     Sahne
    1.13
    eight
    1.09
    three
    1.07
     développer
    1.07
    us
    1.06
    Activations Density 0.031%

    No Known Activations