© 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. 10-GEMMASCOPE-RES-131K
    7. 3814
    Prev
    Next
    INDEX
    Explanations

    relative paths to directories

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

    This neuron detects relative file path references (strings beginning with “…/”) inside HTML or XML attributes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     &
    -2.44
     “
    -2.31
    或
    -2.09
     or
    -2.09
    または
    -2.05
    IUrlHelper
    -2.03
    咵
    -2.02
     to
    -2.00
    ⤞
    -1.96
    のは
    -1.92
    POSITIVE LOGITS
     the
    3.16
    鲠
    2.47
    茳
    2.34
    羕
    2.23
    鹀
    2.20
    之間
    2.17
     linken
    2.16
     unteren
    2.14
    起码
    2.11
     Rückseite
    2.08
    Activations Density 0.006%

    No Known Activations