© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108887
    Prev
    Next
    INDEX
    Explanations

    content delivery networks

    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
    ดอก
    -0.85
     Bluetooth
    -0.75
    NotSupported
    -0.71
     bart
    -0.71
    Ganz
    -0.68
     cytokine
    -0.68
     NFC
    -0.68
    naux
    -0.68
    onta
    -0.67
    glColor
    -0.67
    POSITIVE LOGITS
     CDN
    2.45
    CDN
    2.11
    cdn
    1.56
     Aka
    1.55
    Aka
    1.49
     cd
    1.48
    delivery
    1.36
     delivery
    1.29
     edge
    1.24
     Edge
    1.20
    Activations Density 0.058%

    No Known Activations