© 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. 14743
    Prev
    Next
    INDEX
    Explanations

    references to figures

    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
    ↵
    -1.27
    {~
    -1.13
     každý
    -1.08
     musíte
    -1.04
    方がいい
    -1.01
     olduğ
    -1.01
     Gefang
    -1.01
     गए
    -1.00
     сделали
    -1.00
     faculté
    -0.99
    POSITIVE LOGITS
    Sziasztok
    1.27
    ଵ
    1.16
     groen
    1.11
    före
    1.09
    ﴿
    1.07
     citroen
    1.06
     where
    1.05
    
    1.05
    IMDG
    1.03
     TAMBÉM
    1.03
    Activations Density 0.046%

    No Known Activations