© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94062
    Prev
    Next
    INDEX
    Explanations

    Financial Conduct Authority

    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
     Radiant
    -0.81
    積み
    -0.78
     Cadet
    -0.77
    chu
    -0.76
    ierto
    -0.74
    tm
    -0.73
     bawat
    -0.72
     HAD
    -0.71
    水中
    -0.69
     whiteColor
    -0.68
    POSITIVE LOGITS
     firms
    1.33
     FCA
    1.09
     consumer
    1.05
     Firms
    1.05
    Firm
    1.02
    FCA
    1.02
    utusan
    0.97
    Fir
    0.96
    Consumer
    0.96
     firm
    0.94
    Activations Density 0.011%

    No Known Activations