© 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. 22-GEMMASCOPE-RES-131K
    7. 98188
    Prev
    Next
    INDEX
    Explanations

    Copyright 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_22/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
     new
    -1.25
     any
    -1.23
     in
    -1.09
     when
    -1.04
     provide
    -1.01
    错了
    -1.01
     int
    -1.00
     over
    -0.99
     retail
    -0.98
     often
    -0.98
    POSITIVE LOGITS
     bezw
    1.22
     réun
    1.22
     énorm
    1.18
     gegangen
    1.18
    ulir
    1.17
    Asociación
    1.15
     bewegt
    1.14
     équilibre
    1.13
     quí
    1.12
     gebunden
    1.12
    Activations Density 0.005%

    No Known Activations