© 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. 113228
    Prev
    Next
    INDEX
    Explanations

    words starting questions

    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
     who
    -1.60
    ínű
    -1.45
     but
    -1.40
    ってみる
    -1.40
     use
    -1.39
     types
    -1.39
     equipaje
    -1.38
    though
    -1.38
     prata
    -1.37
     pantalón
    -1.35
    POSITIVE LOGITS
     età
    1.47
    iton
    1.34
    er
    1.33
    จะ
    1.30
    パソコン
    1.28
    などに
    1.28
    おしゃれ
    1.23
     Конечно
    1.23
    </h2>
    1.23
    ación
    1.21
    Activations Density 0.020%

    No Known Activations