© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58469
    Prev
    Next
    INDEX
    Explanations

    devices and displays

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

    The neuron fires on mentions of FPGA hardware and related vendor acronyms (e.g. “FPGA,” “Xilinx,” “Intel”).

    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
     dotyczą
    -1.31
     always
    -1.30
     also
    -1.26
     law
    -1.24
     about
    -1.24
     saying
    -1.20
     שהוא
    -1.20
     last
    -1.19
     jetzt
    -1.18
     siempre
    -1.16
    POSITIVE LOGITS
     milyen
    1.27
    鸸
    1.27
    conversations
    1.27
    𓏸
    1.26
    颔
    1.26
    atigable
    1.20
    內容簡介
    1.18
     abstracto
    1.18
     inginkan
    1.18
    👯
    1.17
    Activations Density 0.310%

    No Known Activations