© 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. 109569
    Prev
    Next
    INDEX
    Explanations

    broadband infrastructure

    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
    孛
    -0.81
     ../../
    -0.80
    proteins
    -0.76
     incarnate
    -0.76
    álja
    -0.75
    ourse
    -0.74
     McDaniel
    -0.74
    fores
    -0.73
    -------
    -0.72
     sandalwood
    -0.72
    POSITIVE LOGITS
    Universal
    1.14
     Universal
    1.11
     universal
    1.09
    Rural
    1.03
     rural
    1.02
     Rural
    0.97
     USDA
    0.94
    universal
    0.92
     broadband
    0.90
     Tribal
    0.88
    Activations Density 0.008%

    No Known Activations