© 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. 40201
    Prev
    Next
    INDEX
    Explanations

    discrete semiconductor devices

    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
     begge
    -1.19
     then
    -1.08
     затем
    -1.05
    gebied
    -1.03
     этих
    -1.02
     alemanes
    -1.02
    がこの
    -1.01
    也是
    -0.98
     этого
    -0.98
     and
    -0.96
    POSITIVE LOGITS
     some
    1.52
     most
    1.40
     for
    1.38
     while
    1.38
     one
    1.21
     whereas
    1.13
     first
    1.13
    Some
    1.11
     Some
    1.09
     older
    1.09
    Activations Density 0.077%

    No Known Activations