© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    engineering and foreign terms

    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
     seksi
    -1.29
    ないです
    -1.25
     Meksi
    -1.22
     vesel
    -1.20
     dakika
    -1.13
     ekos
    -1.13
     sesi
    -1.09
     silikon
    -1.08
     Meksiko
    -1.08
    Only
    -1.07
    POSITIVE LOGITS
     mandatory
    1.09
     obligatory
    1.01
     وزار
    0.98
     required
    0.98
     нар
    0.98
     Nederlandse
    0.98
     Beiträge
    0.96
     core
    0.96
     logits
    0.96
    ęty
    0.96
    Activations Density 0.000%

    No Known Activations