© 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. 75083
    Prev
    Next
    INDEX
    Explanations

    for and to

    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
     from
    -2.00
     with
    -1.77
     theres
    -1.48
     and
    -1.44
     one
    -1.41
    nå
    -1.39
    سد
    -1.38
     there
    -1.37
    فران
    -1.35
    Опис
    -1.30
    POSITIVE LOGITS
     is
    1.73
     usar
    1.50
     jego
    1.49
     quando
    1.48
     cuarenta
    1.48
     najleps
    1.47
    h
    1.45
      
    1.40
     votre
    1.38
    というのは
    1.36
    Activations Density 0.102%

    No Known Activations