© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124112
    Prev
    Next
    INDEX
    Explanations

    served in roles

    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_10/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
     should
    -1.49
     after
    -1.48
     other
    -1.45
     new
    -1.34
     by
    -1.27
    อื่น
    -1.27
     druge
    -1.21
     outras
    -1.17
     before
    -1.13
     having
    -1.13
    POSITIVE LOGITS
     mentre
    1.33
    rehensive
    1.21
    begin
    1.20
     начали
    1.19
     amazingly
    1.19
     then
    1.19
    áže
    1.18
     overly
    1.17
    ție
    1.16
    Tried
    1.16
    Activations Density 0.210%

    No Known Activations