© 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. 31076
    Prev
    Next
    INDEX
    Explanations

    storage units and furniture features

    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
     eikä
    -0.94
    Grath
    -0.93
     Ceiling
    -0.90
     seleccionadas
    -0.89
     chandeliers
    -0.87
    établissement
    -0.83
    Ceiling
    -0.83
    ceiling
    -0.83
    Jupiter
    -0.82
     kitchen
    -0.82
    POSITIVE LOGITS
     shelves
    2.08
     shelf
    1.67
     drawers
    1.61
     drawer
    1.41
     storage
    1.35
    shelf
    1.25
     compartments
    1.25
     slots
    1.16
     Shelf
    1.09
     openings
    1.08
    Activations Density 0.038%

    No Known Activations