© 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. 72763
    Prev
    Next
    INDEX
    Explanations

    acknowledgements and permissions

    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
     report
    -1.52
     same
    -1.13
     respond
    -0.99
     reports
    -0.97
     review
    -0.97
     REPORT
    -0.96
     active
    -0.96
     latter
    -0.94
     others
    -0.94
     Report
    -0.93
    POSITIVE LOGITS
     Penyakit
    1.08
    jarkan
    1.05
     stolet
    1.02
    học
    1.02
    jorde
    1.01
     from
    1.00
     szerző
    1.00
    tieron
    1.00
     jantung
    0.96
     nyel
    0.95
    Activations Density 0.008%

    No Known Activations