© 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. 108133
    Prev
    Next
    INDEX
    Explanations

    vintage new genuine

    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
     would
    -1.09
    Nationalité
    -1.07
     at
    -1.04
     stronę
    -1.03
     had
    -1.00
     ask
    -0.97
     changed
    -0.97
     it
    -0.97
     information
    -0.96
    حسن
    -0.96
    POSITIVE LOGITS
     vintage
    1.72
     Vintage
    1.37
     NEW
    1.34
     gorgeous
    1.30
     Genuine
    1.26
     pair
    1.22
     genuine
    1.20
     magnifiques
    1.20
     WWII
    1.20
    かわいい
    1.17
    Activations Density 0.038%

    No Known Activations