© 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. 33104
    Prev
    Next
    INDEX
    Explanations

    broadcasting corporation

    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
    理
    -0.81
     BAN
    -0.77
    жна
    -0.77
     Adi
    -0.76
    OrEqualTo
    -0.76
     FP
    -0.76
    lium
    -0.76
     kinetics
    -0.75
     mining
    -0.74
    eradish
    -0.73
    POSITIVE LOGITS
     Auntie
    0.96
    BBC
    0.94
    commercial
    0.91
    Corporation
    0.90
     BBC
    0.90
    INTENANCE
    0.86
     öffentlich
    0.84
     ehemal
    0.81
     snipers
    0.80
     Somaliland
    0.80
    Activations Density 0.015%

    No Known Activations