© 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. 90635
    Prev
    Next
    INDEX
    Explanations

    remote access and management

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

    The main thing this neuron does is detect occurrences of “remote” (or “remotely”)—especially when paired with files, sites, access, code, or management.

    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
    <td>
    -1.66
    ใน
    -1.59
     him
    -1.59
    
    -1.52
     aussehen
    -1.44
     hervorragend
    -1.43
    쨩
    -1.42
    راسیون
    -1.41
    鏷
    -1.39
     シューズ
    -1.37
    POSITIVE LOGITS
     remotely
    1.91
     Remote
    1.87
    REMOTE
    1.66
    our
    1.62
     remote
    1.55
     will
    1.54
     for
    1.52
     was
    1.48
    远程
    1.45
     unsere
    1.40
    Activations Density 0.020%

    No Known Activations