© 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. 67131
    Prev
    Next
    INDEX
    Explanations

    physical measurements in pounds

    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
    us
    -1.75
     της
    -1.51
    </h5>
    -1.51
    -1.46
    ouncements
    -1.45
     timmar
    -1.44
    。
    -1.43
     andere
    -1.41
    (
    -1.41
    v
    -1.41
    POSITIVE LOGITS
    本事
    1.88
    bảng
    1.51
    cuerdo
    1.50
     cualquier
    1.49
     Apabila
    1.48
    ctivas
    1.44
     herhangi
    1.43
     dvě
    1.40
     Kemudian
    1.40
     Setelah
    1.40
    Activations Density 0.013%

    No Known Activations