© 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. 128268
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and types

    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
     aerolí
    -1.94
    ﻻ
    -1.88
     fotógrafo
    -1.83
    ﻹ
    -1.79
    ﻷ
    -1.76
    tersebut
    -1.73
     cinturón
    -1.73
    maktadır
    -1.71
    ਖ਼
    -1.70
    MfG
    -1.70
    POSITIVE LOGITS
     will
    2.03
     vielleicht
    2.02
     we
    1.95
     even
    1.73
     newOwner
    1.69
     kurikulum
    1.62
    }
    1.61
    {
    1.60
     аккумулятор
    1.59
     блюдо
    1.55
    Activations Density 0.051%

    No Known Activations