© 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. 34-GEMMASCOPE-RES-131K
    7. 91338
    Prev
    Next
    INDEX
    Explanations

    remote control devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    mario
    -0.73
    ස
    -0.70
     Prov
    -0.70
    icot
    -0.69
    マフラー
    -0.69
     sura
    -0.69
    juma
    -0.69
    惘
    -0.69
    bys
    -0.68
    视
    -0.68
    POSITIVE LOGITS
     remote
    5.91
    remote
    4.91
    Remote
    4.50
     Remote
    4.47
    REMOTE
    3.83
     REMOTE
    3.44
    リモ
    3.42
     remotely
    3.27
    远程
    2.89
     rem
    2.80
    Activations Density 0.049%

    No Known Activations