© 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. 22-GEMMASCOPE-RES-131K
    7. 104505
    Prev
    Next
    INDEX
    Explanations

    rpc, jdbc, exe, glfw, acl

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

    The neuron highlights all‐uppercase technical acronyms or identifiers (e.g. RPC, JDBC, EXE, GLFW).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    潆
    -2.98
    ⚋
    -2.80
    </td>
    -2.67
    
    -2.59
     \
    -2.58
    alahkan
    -2.53
     новая
    -2.44
    聍
    -2.42
    𖤣
    -2.42
    凊
    -2.42
    POSITIVE LOGITS
    to
    2.38
    塒
    2.22
     pembun
    2.13
     gewor
    2.11
    нула
    2.08
    </strong>
    2.02
    ではでは
    2.02
    ти
    1.97
     Там
    1.93
     руке
    1.93
    Activations Density 0.030%

    No Known Activations