© 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. 72371
    Prev
    Next
    INDEX
    Explanations

    Go package declarations

    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
     Projektu
    -1.30
     keinerlei
    -1.26
     kompati
    -1.26
     kooper
    -1.21
     konflikt
    -1.20
    個人的には
    -1.18
    oubtedly
    -1.16
    個人的に
    -1.15
    の中でも
    -1.14
    
    -1.14
    POSITIVE LOGITS
     at
    1.64
     is
    1.41
     has
    1.36
     until
    1.28
     there
    1.19
     without
    1.17
     or
    1.16
     it
    1.16
     before
    1.15
     after
    1.14
    Activations Density 0.020%

    No Known Activations