© 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. 10-GEMMASCOPE-RES-131K
    4. 1447
    Prev
    Next
    INDEX
    Explanations

    testing code and specific queries

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

    The neuron is primarily triggered by Java class or library identifiers (e.g. “Test” and “tika”).

    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
    ș
    -1.77
     encantó
    -1.55
    taya
    -1.42
    </h1>
    -1.40
    antism
    -1.40
    thodoxy
    -1.39
    abytes
    -1.36
    了好
    -1.35
    thodox
    -1.35
     encantan
    -1.34
    POSITIVE LOGITS
     ritard
    1.41
    </em>
    1.30
     bunga
    1.27
     goreng
    1.26
     before
    1.24
    تأ
    1.23
    葙
    1.21
     dollari
    1.19
     to
    1.18
     beurre
    1.17
    Activations Density 0.000%

    No Known Activations