© 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. 2693
    Prev
    Next
    INDEX
    Explanations

    concrete construction materials

    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
     émotion
    -0.77
     cartila
    -0.75
     tweeting
    -0.75
    profesor
    -0.74
     phag
    -0.71
     lacquer
    -0.71
     swamp
    -0.71
    Ǫ
    -0.71
    氬
    -0.70
    сная
    -0.70
    POSITIVE LOGITS
     concrete
    3.88
    Concrete
    3.09
    concrete
    3.02
     Concrete
    2.95
     CONCRETE
    2.44
     бетон
    2.34
     cement
    2.28
     poured
    2.03
     béton
    2.03
     Beton
    2.02
    Activations Density 0.049%

    No Known Activations