© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    models and real-world problems

    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
    fizierung
    -1.17
    eavor
    -1.03
     eri
    -1.03
    گانه
    -1.01
    個月
    -1.01
    heren
    -1.00
    ithin
    -1.00
    
    -0.99
     सुन
    -0.97
    ximate
    -0.97
    POSITIVE LOGITS
     such
    1.30
     examples
    1.16
     situations
    1.11
     revés
    1.09
     Glaube
    1.09
     problems
    1.05
    皈
    1.02
     applications
    1.01
     often
    1.01
    也可
    1.00
    Activations Density 0.127%

    No Known Activations