© 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. 85484
    Prev
    Next
    INDEX
    Explanations

    RS232, CAN, SAN, database, server, steam

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

    The neuron flags mentions of hardware communication interfaces or bus standards (e.g. “RS-232,” “CAN bus”).

    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
     of
    -1.38
    TestingModule
    -1.26
    SizedBox
    -1.14
     through
    -1.10
    heses
    -1.09
     даже
    -1.09
    henden
    -1.09
     during
    -1.09
    rscheinlich
    -1.09
     on
    -1.08
    POSITIVE LOGITS
     here
    1.45
    摆手
    1.29
    truly
    1.22
     burada
    1.21
     tutaj
    1.20
    still
    1.19
     aquí
    1.17
     vencedor
    1.16
    here
    1.16
     penjara
    1.15
    Activations Density 0.244%

    No Known Activations