© 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. 10-GEMMASCOPE-RES-131K
    7. 7811
    Prev
    Next
    INDEX
    Explanations

    shooting and its aftermath

    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_10/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
     görd
    -1.49
    </sup>
    -1.45
     etek
    -1.44
     diki
    -1.43
    ✨✨
    -1.41
     pitié
    -1.38
     europeos
    -1.37
     annons
    -1.37
     senin
    -1.36
     staden
    -1.36
    POSITIVE LOGITS
     from
    1.52
     häufigsten
    1.49
     interacción
    1.49
    contentLoaded
    1.40
    gdala
    1.39
    end
    1.35
    guns
    1.34
     own
    1.33
    たちは
    1.31
    ernacle
    1.30
    Activations Density 0.112%

    No Known Activations