© 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. 33867
    Prev
    Next
    INDEX
    Explanations

    list items, tabs, interface elements

    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
     también
    -1.19
    Also
    -1.16
    矣
    -1.15
     podrían
    -1.14
     também
    -1.09
     лютого
    -1.09
    itzar
    -1.08
     biografias
    -1.08
     Popis
    -1.07
     Âge
    -1.05
    POSITIVE LOGITS
    機能
    1.07
    服务的
    0.99
     roues
    0.98
    大战
    0.95
    บริการ
    0.94
     Funktionen
    0.94
     traseira
    0.93
     active
    0.91
     ceci
    0.91
     social
    0.91
    Activations Density 0.007%

    No Known Activations