© 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. 34-GEMMASCOPE-RES-131K
    7. 62807
    Prev
    Next
    INDEX
    Explanations

    RFID technology and tags

    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
    烛
    -0.73
    ulose
    -0.73
    rodo
    -0.72
    Cus
    -0.72
    çeği
    -0.71
    Snake
    -0.71
     TELEPHONE
    -0.71
    remos
    -0.71
     BAK
    -0.70
    gcs
    -0.70
    POSITIVE LOGITS
     RFID
    2.98
    RFID
    2.25
     tags
    2.03
     tag
    1.91
     Tag
    1.59
     tagging
    1.57
    Tag
    1.55
     identification
    1.53
     tagged
    1.52
     UHF
    1.49
    Activations Density 0.104%

    No Known Activations