© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115907
    Prev
    Next
    INDEX
    Explanations

    LLVM code, android, license, C++, Cat Power

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

    This neuron fires on tokens that appear in XML/URI namespace or schema identifiers (e.g. “android,” “com,” “http,” “schemas,” “www,” “apache,” etc.).

    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
     their
    -1.13
     by
    -1.10
     Mühle
    -0.93
     there
    -0.91
     setValue
    -0.90
     so
    -0.88
    ياه
    -0.85
     all
    -0.85
    كتشاف
    -0.84
    気味
    -0.81
    POSITIVE LOGITS
     inond
    1.03
     delinqu
    0.91
     asemenea
    0.90
    Η
    0.90
    ZI
    0.85
     этих
    0.83
    Pop
    0.83
    kih
    0.82
     тему
    0.82
    向上
    0.82
    Activations Density 0.001%

    No Known Activations