© 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. 93317
    Prev
    Next
    INDEX
    Explanations

    Rom- prefix and root words

    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
     yên
    -0.91
     Decre
    -0.80
    Sono
    -0.79
    ικός
    -0.74
    جنة
    -0.73
    派的
    -0.73
     sintió
    -0.72
    inato
    -0.71
    Along
    -0.70
    uarkan
    -0.69
    POSITIVE LOGITS
    Rom
    1.34
     Rom
    1.26
     rom
    0.97
    romp
    0.97
     novels
    0.89
    ulus
    0.88
     ROM
    0.88
    Romans
    0.86
     IMAGE
    0.83
     Rome
    0.81
    Activations Density 0.017%

    No Known Activations