© 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. 25654
    Prev
    Next
    INDEX
    Explanations

    import aliases, class names

    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
     as
    -2.38
    =
    -1.20
    ()==
    -1.13
     как
    -1.06
     =
    -1.05
     jako
    -1.04
     качестве
    -1.04
    FactoryBean
    -1.03
    의
    -1.01
     ==
    -1.00
    POSITIVE LOGITS
     अन्य
    1.20
     innych
    1.17
     パネル
    0.98
     fournisse
    0.95
     pollici
    0.92
     riktigt
    0.92
    minator
    0.91
    如何在
    0.90
    Tē
    0.89
     governador
    0.89
    Activations Density 0.040%

    No Known Activations