© 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. 38612
    Prev
    Next
    INDEX
    Explanations

    store shelves

    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
    Uf
    -0.75
     préparer
    -0.72
    曄
    -0.72
    ytet
    -0.72
    Emple
    -0.72
    dying
    -0.71
     Headquarters
    -0.71
     Heer
    -0.70
    revolutionary
    -0.70
     piezas
    -0.69
    POSITIVE LOGITS
     shelves
    3.81
     shelf
    3.64
    shelf
    2.69
     Shelf
    2.63
    Shelf
    2.42
     Shelves
    2.38
     shelving
    2.30
     shel
    2.30
    shel
    2.14
    Shel
    1.91
    Activations Density 0.039%

    No Known Activations