© 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. 98560
    Prev
    Next
    INDEX
    Explanations

    Romans chapter

    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
    ⊃
    -0.82
    ешься
    -0.80
    ristown
    -0.80
     arrancar
    -0.79
    沟
    -0.78
    Zé
    -0.78
    ﺧ
    -0.77
    bisoft
    -0.77
    Ⓢ
    -0.76
     októ
    -0.75
    POSITIVE LOGITS
     Romans
    2.66
    Romans
    2.39
     Rom
    2.00
    Rom
    1.94
     Roman
    1.64
     Rome
    1.59
    罗马
    1.49
     ROM
    1.48
    rom
    1.42
     romans
    1.40
    Activations Density 0.004%

    No Known Activations