© 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. 10-GEMMASCOPE-RES-131K
    7. 39498
    Prev
    Next
    INDEX
    Explanations

    process of urbanization and miniaturization

    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_10/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
     this
    -1.93
     erwäh
    -1.65
     these
    -1.61
    ときは
    -1.61
     cuyo
    -1.60
    idemiology
    -1.57
    one
    -1.56
     cuyos
    -1.55
    «
    -1.51
     originali
    -1.49
    POSITIVE LOGITS
    </h4>
    1.81
     أجل
    1.73
    𓍊
    1.73
    </sup>
    1.68
    Previews
    1.50
    США
    1.48
     pokra
    1.46
    摸了
    1.45
    Suka
    1.45
    Merk
    1.45
    Activations Density 0.062%

    No Known Activations