© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    data packets, messages, or code

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

    technical descriptions of data packets, their structure, and fields in network protocols and programming contexts.

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

    This neuron flags verbs that denote inclusion or carrying of data (e.g., “contain,” “include,” “carries”) in network packet descriptions.

    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
     ziren
    -1.34
     in
    -1.25
    umerable
    -1.07
    Boton
    -1.07
     структур
    -1.04
    meture
    -1.02
    ÇÃO
    -1.02
    ℠
    -1.02
    Tobacco
    -1.02
     without
    -1.00
    POSITIVE LOGITS
     that
    1.60
     όταν
    1.45
     message
    1.38
     muualla
    1.34
    MatIconModule
    1.30
    PENDAHULUAN
    1.28
     communication
    1.25
     ότι
    1.24
     иногда
    1.21
    PageRoute
    1.21
    Activations Density 0.168%

    No Known Activations