© 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. 84850
    Prev
    Next
    INDEX
    Explanations

    Memphis Pyramid

    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
     PSU
    -0.80
     matte
    -0.74
     réput
    -0.71
     tæ
    -0.70
     scallo
    -0.70
    profil
    -0.69
     Namibia
    -0.68
     exponentially
    -0.68
    珍珠
    -0.67
     Mauer
    -0.67
    POSITIVE LOGITS
     Memphis
    2.47
    Memphis
    2.42
     memp
    1.64
     Grizzlies
    1.41
    memp
    1.40
     FedEx
    1.20
     MEM
    1.16
     Mississippi
    1.15
     Beale
    1.14
     Shelby
    1.10
    Activations Density 0.040%

    No Known Activations