© 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. 39638
    Prev
    Next
    INDEX
    Explanations

    code delimiters `<` `>` `"` `:`

    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
     perioden
    -1.26
     první
    -1.23
     prouver
    -1.20
     cinquième
    -1.19
     kampen
    -1.19
     forbindelse
    -1.16
     befolk
    -1.16
     pomocí
    -1.13
     kalender
    -1.13
    もうすぐ
    -1.13
    POSITIVE LOGITS
    </em>
    1.17
     a
    1.13
     especially
    1.09
    </i>
    1.09
     an
    1.06
     maybe
    1.06
     probably
    1.06
     latter
    1.06
     have
    1.05
     possibly
    1.05
    Activations Density 0.003%

    No Known Activations