© 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. 34-GEMMASCOPE-RES-131K
    7. 107954
    Prev
    Next
    INDEX
    Explanations

    box and related phrases

    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
     玫瑰
    -1.09
     syndical
    -1.07
    安卓
    -0.96
    包围
    -0.96
     Transmit
    -0.96
     黑白
    -0.96
     Mondial
    -0.96
     regarded
    -0.93
     amour
    -0.93
     loh
    -0.92
    POSITIVE LOGITS
     box
    1.58
     Box
    1.39
     boxes
    1.27
     ボックス
    1.20
     Boxes
    1.16
     передач
    1.16
    📦
    1.12
     contents
    1.10
     cajas
    1.09
    boxes
    1.08
    Activations Density 0.034%

    No Known Activations