© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92320
    Prev
    Next
    INDEX
    Explanations

    U.S. Supreme Court citations

    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_34/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
     londres
    -0.80
     might
    -0.79
     volte
    -0.79
     medicines
    -0.77
     поки
    -0.77
     economies
    -0.77
    本体
    -0.77
     what
    -0.77
    хам
    -0.75
    𝚎
    -0.75
    POSITIVE LOGITS
    beginning
    0.84
    рант
    0.81
     devote
    0.78
    annis
    0.78
     embarazo
    0.77
     asesoramiento
    0.77
     безу
    0.77
    いただく
    0.76
     trám
    0.76
     髪
    0.75
    Activations Density 0.044%

    No Known Activations