© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49187
    Prev
    Next
    INDEX
    Explanations

    car interiors

    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
     enzymes
    -0.81
    ım
    -0.81
     Gebäude
    -0.80
    就这么
    -0.79
     внешний
    -0.78
    lijkse
    -0.77
     população
    -0.75
    kur
    -0.73
    øb
    -0.72
     อย
    -0.71
    POSITIVE LOGITS
     interior
    4.00
     interiors
    3.16
    interior
    3.05
    Interior
    2.81
     Interior
    2.77
     wnętr
    2.52
     intérieur
    2.41
    INTERIOR
    2.27
     interiores
    2.25
     INTERIOR
    2.22
    Activations Density 0.018%

    No Known Activations