© 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. 73065
    Prev
    Next
    INDEX
    Explanations

    greetings and announcements

    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
     luz
    -1.13
     mentales
    -1.12
     Recife
    -1.10
    ẓ
    -1.08
     jolie
    -1.08
     ojo
    -1.03
     نوشت
    -1.03
     btn
    -1.03
     белые
    -1.02
     inuti
    -1.02
    POSITIVE LOGITS
     your
    1.80
     here
    1.72
     today
    1.66
     tonight
    1.65
     you
    1.55
     yourselves
    1.27
     this
    1.25
     đây
    1.22
     čia
    1.21
     verwacht
    1.13
    Activations Density 0.020%

    No Known Activations