© 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. 102432
    Prev
    Next
    INDEX
    Explanations

    place as a location

    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
     ceea
    -1.04
    用的
    -1.00
     manguera
    -0.95
    いただけます
    -0.94
     какие
    -0.93
     tracción
    -0.91
     posibilidades
    -0.90
     Gefäng
    -0.89
    ╖
    -0.89
     estaciones
    -0.87
    POSITIVE LOGITS
     to
    3.27
     for
    2.09
     where
    1.52
     لل
    1.06
     для
    1.01
     相談
    0.99
     où
    0.97
     berge
    0.97
     stille
    0.96
    lugar
    0.90
    Activations Density 0.028%

    No Known Activations