© 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. 110761
    Prev
    Next
    INDEX
    Explanations

    chipset names and architectures

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

    references to embedded systems, development boards, and hardware specifications (particularly ARM-based single-board computers and microcontrollers).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects technical bootloader and single‐board computer terminology, such as “boot,” “coreboot,” “U-boot,” NAND/MMC, and board model identifiers.

    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
     aéreas
    -1.59
    tedrale
    -1.52
     /\.(
    -1.45
    傒
    -1.44
    俛
    -1.39
    
    -1.38
     большие
    -1.37
     imprend
    -1.36
    endforeach
    -1.32
    +/**
    -1.32
    POSITIVE LOGITS
    2
    1.28
    Arbe
    1.23
     Gelder
    1.19
    UNIVERSIDAD
    1.19
    Yog
    1.19
     обеспечить
    1.17
     сохранить
    1.16
     hjäl
    1.16
    Frid
    1.14
    CIUDAD
    1.13
    Activations Density 0.063%

    No Known Activations