© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130942
    Prev
    Next
    INDEX
    Explanations

    coordinates with comparisons

    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
     вместо
    -1.09
    instead
    -1.04
    Instead
    -1.01
    jMenuItem
    -0.99
     Produit
    -0.98
    jangan
    -0.97
    ㈰
    -0.97
     longues
    -0.96
     Ministère
    -0.94
    ครื่อง
    -0.93
    POSITIVE LOGITS
     between
    1.05
     to
    1.02
     group
    0.98
     comparing
    0.93
     most
    0.93
     under
    0.93
     against
    0.89
     investigating
    0.88
     like
    0.88
     around
    0.88
    Activations Density 0.028%

    No Known Activations