© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109153
    Prev
    Next
    INDEX
    Explanations

    country codes, state abbreviations

    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
    ẓ
    -0.90
    OTHY
    -0.89
    AGON
    -0.79
    underscore
    -0.76
    IENT
    -0.75
    nią
    -0.75
     ngàn
    -0.75
    niego
    -0.75
     Definitions
    -0.75
     heim
    -0.74
    POSITIVE LOGITS
     CA
    1.23
     VA
    1.20
     DA
    1.17
     BA
    1.15
     OA
    1.13
     HA
    1.09
     EA
    1.09
     UA
    1.05
     CU
    1.04
     IA
    1.03
    Activations Density 0.182%

    No Known Activations