© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65643
    Prev
    Next
    INDEX
    Explanations

    Spain, Madrid, locations

    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
     Chávez
    -1.52
     centavos
    -1.22
     Agosto
    -1.22
     libras
    -1.19
     sombr
    -1.18
     vasto
    -1.18
     sirena
    -1.16
     emporio
    -1.16
     colina
    -1.16
     fortific
    -1.15
    POSITIVE LOGITS
     Tx
    1.27
     comprobar
    1.11
    Tx
    1.07
     Spain
    1.05
     habitual
    1.04
     tx
    1.02
    tx
    1.01
     supposes
    1.01
     €
    1.00
    lilla
    1.00
    Activations Density 0.611%

    No Known Activations