© 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. 82473
    Prev
    Next
    INDEX
    Explanations

    adding or mapping data

    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
     Lotto
    -0.80
    ამ
    -0.78
    undang
    -0.74
    itope
    -0.68
     batte
    -0.68
     βο
    -0.68
    ͬ
    -0.67
     Dems
    -0.66
    Reise
    -0.66
     Malik
    -0.65
    POSITIVE LOGITS
     put
    3.33
    put
    3.28
    Put
    2.88
     Put
    2.78
     PUT
    2.56
    PUT
    2.34
     puts
    2.30
     putting
    2.25
    putting
    2.11
    puts
    1.93
    Activations Density 0.004%

    No Known Activations