© 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. 79768
    Prev
    Next
    INDEX
    Explanations

    steps in a process

    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
     this
    -1.21
    recently
    -1.20
     recente
    -1.15
    strongly
    -1.15
    Likewise
    -1.14
     bosques
    -1.12
    特意
    -1.12
    recent
    -1.12
    Instead
    -1.11
    Tür
    -1.09
    POSITIVE LOGITS
     then
    2.20
     and
    1.67
     затем
    1.39
     began
    1.37
     Then
    1.36
     THEN
    1.33
     decide
    1.27
     entweder
    1.27
     rồi
    1.25
     begin
    1.24
    Activations Density 0.029%

    No Known Activations