© 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. 83777
    Prev
    Next
    INDEX
    Explanations

    completed on ()

    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
    deburg
    -0.79
     Mange
    -0.77
     {
    -0.75
     useCallback
    -0.74
     senz
    -0.73
    INIS
    -0.73
     decided
    -0.73
    🪸
    -0.73
     pathetic
    -0.73
     affected
    -0.72
    POSITIVE LOGITS
     plotly
    0.83
    بدأ
    0.81
     hodnot
    0.81
    虎
    0.79
     stigmati
    0.77
    zte
    0.76
     episodes
    0.75
    webtoken
    0.75
     charbon
    0.75
     spiders
    0.74
    Activations Density 0.002%

    No Known Activations