© 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. 25887
    Prev
    Next
    INDEX
    Explanations

    code get/set properties

    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
    ßt
    -1.18
    釙
    -1.15
     otorga
    -1.12
    represents
    -1.12
     höl
    -1.11
     regresó
    -1.09
    
    -1.09
    Throwaway
    -1.08
    matische
    -1.07
     akku
    -1.07
    POSITIVE LOGITS
     or
    1.13
     if
    1.13
     we
    0.97
     олив
    0.95
     should
    0.94
     you
    0.94
    Ku
    0.94
    ācija
    0.93
     checking
    0.93
     I
    0.93
    Activations Density 0.001%

    No Known Activations