© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38938
    Prev
    Next
    INDEX
    Explanations

    code definitions and variable assignments

    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
     ſol
    -1.15
     ſur
    -1.07
    usual
    -1.07
     rumore
    -1.07
     markt
    -1.05
    雠
    -1.05
     itſelf
    -1.05
    ኵ
    -1.05
     hiel
    -1.04
     galo
    -1.04
    POSITIVE LOGITS
     from
    1.20
     daudz
    0.96
     csomag
    0.94
     takiego
    0.94
    क़
    0.91
     jūs
    0.89
     「
    0.89
     ``
    0.87
     tikai
    0.87
    смо
    0.85
    Activations Density 0.026%

    No Known Activations