© 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. 67290
    Prev
    Next
    INDEX
    Explanations

    university and news abbreviations

    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
    ického
    -1.48
    </h4>
    -1.48
    pilih
    -1.38
    vestidos
    -1.27
    Đặc
    -1.27
    getUid
    -1.27
     settimane
    -1.27
     alrededores
    -1.23
     sesuatu
    -1.23
    områ
    -1.22
    POSITIVE LOGITS
    </i>
    1.58
    :
    1.42
    between
    1.32
    を高
    1.25
    या
    1.21
    wide
    1.21
     dança
    1.20
    from
    1.20
     grâce
    1.20
    since
    1.19
    Activations Density 0.050%

    No Known Activations