© 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. 116063
    Prev
    Next
    INDEX
    Explanations

    #include statements

    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
     dlaczego
    -1.20
     why
    -1.14
     that
    -1.05
    んですよ
    -1.01
     gezwungen
    -1.00
    jsdelivr
    -0.98
     چیست
    -0.95
    んですよね
    -0.95
     PROCEEDINGS
    -0.94
    おわりに
    -0.94
    POSITIVE LOGITS
     also
    1.54
     “
    1.29
     "
    1.26
    formatie
    1.04
     «
    1.02
     „
    1.01
     также
    0.99
     también
    0.98
     ……
    0.96
    だった
    0.96
    Activations Density 0.031%

    No Known Activations