© 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. 110671
    Prev
    Next
    INDEX
    Explanations

    `pragma`, `Q`, `As`, `Proverbs`

    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
    🏻
    -0.99
     mana
    -0.83
     instig
    -0.77
    éndole
    -0.74
    Importante
    -0.73
     Tris
    -0.71
    明顯
    -0.71
    巿
    -0.71
     frontera
    -0.71
     différence
    -0.70
    POSITIVE LOGITS
    🏾
    1.48
    African
    1.05
     Diaspora
    1.00
     Osun
    0.99
     Uhuru
    0.99
     tryna
    0.98
     African
    0.97
     Sank
    0.95
     Spann
    0.95
     Crear
    0.94
    Activations Density 0.000%

    No Known Activations