© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25495
    Prev
    Next
    INDEX
    Explanations

    founded in

    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
     It
    -1.51
     temos
    -1.30
     which
    -1.30
    standigheden
    -1.24
     {
    -1.24
     $
    -1.21
     stanovnika
    -1.20
    foreach
    -1.18
    嚆
    -1.17
     antes
    -1.13
    POSITIVE LOGITS
    Exeunt
    1.26
    يلات
    1.23
    Bila
    1.23
     verschillen
    1.23
    
    1.20
     basteln
    1.18
     and
    1.18
     dezelfde
    1.14
    是怎么回事
    1.13
    tamil
    1.13
    Activations Density 0.104%

    No Known Activations