© 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. 94064
    Prev
    Next
    INDEX
    Explanations

    Windows Live

    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
     Soccer
    -0.90
     brugt
    -0.88
    ộn
    -0.82
    ниц
    -0.81
     Apartments
    -0.80
     billeder
    -0.80
    🙄
    -0.79
    tidas
    -0.79
     illnesses
    -0.79
     Floren
    -0.79
    POSITIVE LOGITS
     test
    1.01
     Test
    0.88
    Resultados
    0.83
     feel
    0.82
    FRIEND
    0.81
    test
    0.81
     nochmal
    0.81
     olika
    0.79
     varies
    0.78
    Interesting
    0.77
    Activations Density 0.000%

    No Known Activations