© 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. 34-GEMMASCOPE-RES-131K
    7. 65354
    Prev
    Next
    INDEX
    Explanations

    code preprocessing directives and includes

    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_34/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
     then
    -1.98
     سپس
    -1.27
     kemudian
    -1.26
     but
    -1.23
     één
    -1.22
    Then
    -1.19
     THEN
    -1.18
    但是
    -1.16
     Then
    -1.15
    ffiche
    -1.15
    POSITIVE LOGITS
     No
    1.16
     None
    1.07
     just
    1.06
    no
    1.06
     “
    1.05
     NO
    1.01
    –
    0.96
     simply
    0.96
      
    0.94
     –
    0.94
    Activations Density 0.004%

    No Known Activations