© 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. 73095
    Prev
    Next
    INDEX
    Explanations

    Fay, Faye, and place names

    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
    ن
    -2.66
     detención
    -2.39
     estadía
    -2.30
    ஂ
    -2.27
    erintah
    -2.27
     และ
    -2.25
    ン
    -2.23
    は
    -2.22
     enters
    -2.20
     renuncia
    -2.20
    POSITIVE LOGITS
     uſed
    2.97
    ﮩ
    2.78
    k
    2.59
    geſ
    2.58
    想
    2.45
    优点
    2.39
    癀
    2.25
    {
    2.16
    )
    2.13
    螄
    2.13
    Activations Density 0.002%

    No Known Activations