© 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. 30710
    Prev
    Next
    INDEX
    Explanations

    internet and broadband access

    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
     Bidang
    -0.83
    anilla
    -0.79
    흩
    -0.74
    baño
    -0.73
    fich
    -0.72
    orenje
    -0.71
    bige
    -0.70
     BCD
    -0.70
     CASS
    -0.69
     aperto
    -0.69
    POSITIVE LOGITS
     internet
    2.86
     Internet
    2.48
     broadband
    2.44
     speeds
    2.34
     speed
    2.13
    internet
    2.09
    Internet
    1.95
     fiber
    1.95
     bandwidth
    1.95
     fibre
    1.91
    Activations Density 0.036%

    No Known Activations