© 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. 64998
    Prev
    Next
    INDEX
    Explanations

    telecom broadband fiber

    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
     мать
    -0.96
    CONCLUSIONES
    -0.95
     القوات
    -0.94
     bocas
    -0.92
     BIM
    -0.90
    ༧
    -0.86
    idious
    -0.85
    דול
    -0.84
    Ekster
    -0.84
     niente
    -0.84
    POSITIVE LOGITS
     broadband
    1.98
     fiber
    1.90
     Broadband
    1.70
     subscriber
    1.69
     wireless
    1.66
     telecom
    1.65
     Fiber
    1.56
     fibre
    1.46
    Fiber
    1.46
    telecom
    1.45
    Activations Density 0.063%

    No Known Activations