© 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. 39970
    Prev
    Next
    INDEX
    Explanations

    rpc and ipc communication

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

    This neuron fires on all-caps technical acronyms or initialisms (e.g., OMG, IOR, RPC, DBUS).

    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
     cappello
    -1.80
     piú
    -1.70
     lettore
    -1.70
     cappuccio
    -1.63
     dubbio
    -1.63
     steder
    -1.63
     peccato
    -1.63
     vuol
    -1.60
     oggetto
    -1.59
     sepol
    -1.57
    POSITIVE LOGITS
    the
    1.47
    </strong>
    1.41
    1
    1.40
    -
    1.36
    neling
    1.36
     its
    1.31
    prime
    1.26
     D
    1.22
     
    1.20
     B
    1.19
    Activations Density 0.046%

    No Known Activations