© 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. 26414
    Prev
    Next
    INDEX
    Explanations

    file paths and extensions

    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
     just
    -2.03
     with
    -1.93
     in
    -1.93
     because
    -1.93
     furthering
    -1.90
     before
    -1.89
     by
    -1.88
     two
    -1.88
     epitom
    -1.84
     from
    -1.81
    POSITIVE LOGITS
     Dinas
    1.75
     semelh
    1.54
    皷
    1.52
     lauded
    1.50
    both
    1.50
    
    1.49
    厹
    1.49
     CURRENT
    1.49
    almost
    1.44
     astounding
    1.44
    Activations Density 0.013%

    No Known Activations